--- name: pipeline description: | Pipeline orchestrator for idstack. Chains skills from /needs-analysis through /course-export in evidence-based order, auto-skipping completed skills. Handles fresh starts (no manifest) and resumption (partial pipeline). (idstack) allowed-tools: - Bash - Read - Write - Edit - Glob - Grep - Skill - AskUserQuestion --- ## Preamble: Interaction Conventions idstack runs in Claude Code. Skill bodies use a few **concept names** for the tools they lean on: - **AskUserQuestion** — when a skill says "ask via AskUserQuestion" or "using AskUserQuestion", it means: present a single multiple-choice question (e.g., "Which of these best describes X?") and stop, waiting for the user's answer before proceeding. Ask **one** question at a time, never batch. This maps to the `AskUserQuestion` tool. - **Agent (sub-task dispatch)** — when a skill says "if the Agent tool is available, dispatch X as a sub-task," that is a parallelization shortcut, never the definition of the work. The inline written-out steps that follow are; run them sequentially whenever dispatch is unavailable or fails. Four skills use it: accessibility-review, course-builder, course-quality-review, and red-team. - **Skill (cross-skill invocation)** — used only by `/idstack:pipeline`, which invokes each child skill in-process via the `Skill` tool. - **Skill invocation syntax in user-facing text** — every skill is invoked as `/idstack:`. Always write the namespaced form: a bare `/` is not a valid command. This applies in reports, manifests, and AskUserQuestion options as much as in chat output. These are **directives to the model**, not magic words — interpret them as the protocol above. ## Preamble: Writing Standard (ASD-STE100) All text that idstack writes for a person must obey the rules in this section. This includes chat text, AskUserQuestion questions and options, HTML reports, the course dashboard, course content for learners, and export packages. `bin/idstack-ste-check` reads the word list between the two `ste-core` markers. `extension/shared/ste-rules.js` has a copy of the text between the markers. If you change this text, change the copy at the same time. The rules also apply to the text that idstack writes in `.idstack/project.json` and in learnings, for example finding text and recommendations. Other skills use this text in their output. The checker does not read these files. Do not change text that comes from the course. Do not change JSON keys or the values that a script or a skill reads. Writing standard: ASD-STE100 Simplified Technical English (STE) This summary uses the ASD-STE100 writing rules. ASD does not endorse idstack. This summary does not replace the ASD-STE100 standard. Use these rules only for text in English. If the text is not in English, do not use these rules. Words: - Use one word for one meaning. Use the same term for the same item in all of the text. - Use short words that are easy to understand. Do not use the words in the first column of the word list. - Use the technical nouns and technical verbs of instructional design when no simple word has the same meaning. Examples of technical nouns are learning objective, ILO, rubric, criterion, formative assessment, scaffold, cognitive load, meta-analysis, evidence tier, finding and severity. - The Bloom's taxonomy verbs are technical verbs. Examples are remember, understand, apply, analyze, evaluate, create, assess, critique, demonstrate, design and implement. Use them in learning objectives and in text about Bloom's levels. - Software verbs are technical verbs. Examples are run, click, open, save, install and update. - Do not use a technical noun as a verb. - Do not use contractions. Write "do not", not "don't". - Do not use Latin abbreviations. Write "for example", not "e.g.". Verbs: - Use the active voice. In a description, use the passive voice only when you do not know who or what does the work. - Use only the simple tenses. Write "writes", "wrote" or "will write". Do not write "has written", "had written" or "is writing". - Do not use a verb that ends in "-ing". You can use an "-ing" word only in a technical noun, for example "learning objective". Sentences: - Write one topic in each sentence. - An instruction has a maximum of 20 words. A description has a maximum of 25 words. - Do not remove words, for example "the", "a" and "is", to make a sentence shorter. - A noun cluster has a maximum of three nouns. - Do not use semicolons. Write two sentences. - Use a vertical list for text that has many parts. Instructions and descriptions: - Write an instruction as a command. Write one instruction in each sentence. Give a number to each step. - If the reader must know a condition first, write the condition first. Example: "If the course has no rubric, add a rubric." - Do not write commands in a description. A paragraph has one topic and a maximum of six sentences. Recommendations: - First show the problem that idstack found. Then show the evidence. Then give the recommendation. - In a description, write a recommendation as "idstack recommends that you ..." or as "You can ...". - In a numbered list of steps, write each step as a command. - Do not use "consider", "may", "should" or "suggest". Text that you do not change: - Do not change a quotation from a course, a person, a standard or a different software tool. Put each quotation in quotation marks. A new version of a text is not a quotation. Write it with these rules. - Do not change code, file names, commands, URLs, citations, for example [Domain-N] [T1], or the names of products and standards. Word list. Do not use the word in the first column. Use the word in the second column. | Do not use | Use | Note | |---|---|---| | "utilize" | "use" | | | "ensure" | "make sure" | | | "verify" | "make sure" | | | "confirm" | "make sure" | | | "commence" | "start" | | | "begin" | "start" | | | "initiate" | "start" | | | "terminate" | "stop" | | | "prior to" | "before" | | | "in order to" | "to" | | | "assist" | "help" | | | "facilitate" | "help" | | | "obtain" | "get" | | | "achieve" | "get" | | | "require" | "necessary" | | | "indicate" | "show" | | | "appear" | "show" | | | "consider" | "idstack recommends that you" or "think about" | | | "suggest" | "recommend" | | | "suggestion" | "recommendation" | | | "may" | "can" | lowercase only | | "might" | "can" | | | "should" | "must" or "idstack recommends that you" | | | "would" | "can" | | | "shall" | "must" | | | "perform" | "do" | | | "accomplish" | "do" | | | "additional" | "more" | | | "numerous" | "many" | | | "enough" | "sufficient" | | | "provide" | "give" | | | "allow" | "let" | | | "choose" | "select" | | | "determine" | "find" | | | "locate" | "find" | | | "modify" | "change" | | | "attempt" | "try" | | | "therefore" | "thus" | | | "however" | "but" | | | "whether" | "if" | | | "via" | "through" | | | "upon" | "on" | | | "such as" | "for example" | | | "e.g." | "for example" | | | "i.e." | "that is" | | | "etc." | (write the full list) | | | "please" | (remove the word) | | How to use the standard: 1. If the conversation or the course is not in English, do not run the checker. 2. When you write a file for a person, run `bin/idstack-ste-check` on it at the step that the skill shows. 3. If the checker shows problems, write each sentence that it shows again. Then write the file again and run the checker again. 4. Run the checker a maximum of three times. If problems stay after the third time, tell the user which lines have problems. 5. If the checker does not run, continue the skill. Tell the user one time that the check did not run. The checker finds only some problems: long sentences, long paragraphs, semicolons, contractions, "has been" verbs and the words in the word list. Apply all of the rules when you write. The verbosity and experience settings change how much you write. They do not change these rules. Identify text from a different source for the checker: - In HTML, put a short quotation in `` and a long quotation in `
`. If a full list item or table cell is a quotation, add `data-ste="quoted"` to that element. - In Markdown, put a long quotation on lines that start with `> `. Put a short quotation in quotation marks. - The name of a standard or a principle can have a word from the word list. Identify that name as a short quotation. Example: `3.3.3 Error Suggestion`. - The checker counts each quotation, citation, code span and placeholder as one word. When a skill sends work to a sub-agent, put a copy of this section in the sub-agent prompt. The sub-agent cannot see this preamble. Example sentences in a skill show the content of a message. Write them in STE when you use them. ## Preamble: Update Check ```bash # Resolve the idstack install dir. Re-derived at the top of every bash block — # blocks run in separate shells, so a value derived in an earlier block is not # available here. Priority: explicit env overrides, then the Claude Code # marketplace cache (highest version). Empty if none found; guard # "$_IDSTACK/bin/..." calls accordingly. # Canonical copy: templates/snippets/idstack-resolve.sh (the IDSTACK_RESOLVE # placeholder in skill templates) — keep this block identical to it. _IDSTACK="" # Marketplace cache holds one dir per installed version. Sort the basenames by # numeric version fields, not lexically — plain sort ranks 3.9.0.0 above # 3.10.0.0 and would pick a stale install once the minor hits double digits. _idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack" _idstack_cache="" if [ -d "$_idstack_cache_root" ]; then _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1) [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v" fi for _p in "${CLAUDE_PLUGIN_ROOT:-}" "${IDSTACK_HOME:-}" "$_idstack_cache"; do if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi done _UPD=$("$_IDSTACK/bin/idstack-update-check" 2>/dev/null || true) [ -n "$_UPD" ] && echo "$_UPD" ``` If the output contains `UPDATE_AVAILABLE`: tell the user "A newer version of idstack is available. Run `cd $_IDSTACK && git pull && ./setup` to update. (The `./setup` step is required — it cleans up legacy symlinks.)" Then continue normally. ## Preamble: Project Manifest Before starting, check for an existing project manifest. ```bash # (fresh shell — re-derive the install dir; see Preamble: Update Check) _IDSTACK="" # Marketplace cache holds one dir per installed version. Sort the basenames by # numeric version fields, not lexically — plain sort ranks 3.9.0.0 above # 3.10.0.0 and would pick a stale install once the minor hits double digits. _idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack" _idstack_cache="" if [ -d "$_idstack_cache_root" ]; then _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1) [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v" fi for _p in "${CLAUDE_PLUGIN_ROOT:-}" "${IDSTACK_HOME:-}" "$_idstack_cache"; do if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi done if [ -f ".idstack/project.json" ]; then echo "MANIFEST_EXISTS" "$_IDSTACK/bin/idstack-migrate" .idstack/project.json 2>/dev/null || cat .idstack/project.json else echo "NO_MANIFEST" fi ``` **If MANIFEST_EXISTS:** - Read the manifest. If the JSON is malformed, report the specific parse error to the user, offer to fix it, and STOP until it is valid. Never silently overwrite corrupt JSON. - Preserve all existing sections when writing back. **If NO_MANIFEST:** - This skill will create or update the manifest during its workflow. ## Preamble: Preferences ```bash if [ -f ".idstack/project.json" ] && command -v python3 &>/dev/null; then python3 -c " import json, sys try: data = json.load(open('.idstack/project.json')) prefs = data.get('preferences', {}) v = prefs.get('verbosity', 'normal') if v != 'normal': print(f'VERBOSITY:{v}') except: pass " 2>/dev/null || true fi ``` **If VERBOSITY:concise:** Keep explanations brief. Skip evidence citations inline (still follow evidence-based recommendations, just don't cite tier codes in output). **If VERBOSITY:detailed:** Include full evidence citations, alternative approaches considered, and rationale for each recommendation. **If VERBOSITY:normal or not shown:** Default behavior — cite evidence tiers inline, explain key decisions, skip exhaustive alternatives. ## Preamble: Designer Profile ```bash _PROFILE="$HOME/.idstack/profile.yaml" if [ -f "$_PROFILE" ]; then # Simple YAML parsing for experience_level (no dependency needed) _EXP=$(grep -E '^experience_level:' "$_PROFILE" 2>/dev/null | sed 's/experience_level:[[:space:]]*//' | tr -d '"' | tr -d "'") [ -n "$_EXP" ] && echo "EXPERIENCE:$_EXP" else echo "NO_PROFILE" fi ``` **If EXPERIENCE:novice:** Provide more context for recommendations. Explain WHY each step matters, not just what to do. Define jargon on first use. Offer examples. **If EXPERIENCE:intermediate:** Standard explanations. Assume familiarity with instructional design concepts but explain idstack-specific patterns. **If EXPERIENCE:expert:** Be concise. Skip basic explanations. Focus on evidence tiers, edge cases, and advanced considerations. Trust the user's domain knowledge. **If NO_PROFILE:** On first run, after the main workflow is underway (not before), mention: "Tip: create `~/.idstack/profile.yaml` with `experience_level: novice|intermediate|expert` to adjust how much detail idstack provides." ## Preamble: Evidence Engine & Consensus QA Check whether a Consensus API key is configured for live literature grounding. ```bash # Consensus key detection # (fresh shell — re-derive the install dir; see Preamble: Update Check) _IDSTACK="" _idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack" _idstack_cache="" if [ -d "$_idstack_cache_root" ]; then _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1) [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v" fi for _dir in "${CLAUDE_PLUGIN_ROOT:-}" "${IDSTACK_HOME:-}" "$_idstack_cache"; do if [ -n "$_dir" ] && [ -d "$_dir" ]; then _IDSTACK="${_dir%/}"; break; fi done _CONSENSUS_KEY=$("$_IDSTACK/bin/idstack-consensus" status 2>/dev/null | grep -q '"api_key_configured": true' && echo "CONFIGURED" || echo "UNCONFIGURED") [ -n "$_CONSENSUS_KEY" ] && echo "CONSENSUS:$_CONSENSUS_KEY" ``` **If CONFIGURED:** Live literature grounding via Consensus API is active. Novel and subject-specific pedagogical claims will be verified against peer-reviewed research. **If UNCONFIGURED:** Running in zero-key mode using the curated evidence base. On first run, after the main workflow is underway (not before), mention: "Tip: Set CONSENSUS_API_KEY to enable live literature verification via Consensus." ## Preamble: Context Recovery Check for session history and learnings from prior runs. ```bash # Context recovery: timeline + learnings # (fresh shell — re-derive the install dir; see Preamble: Update Check) _IDSTACK="" # Marketplace cache holds one dir per installed version. Sort the basenames by # numeric version fields, not lexically — plain sort ranks 3.9.0.0 above # 3.10.0.0 and would pick a stale install once the minor hits double digits. _idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack" _idstack_cache="" if [ -d "$_idstack_cache_root" ]; then _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1) [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v" fi for _p in "${CLAUDE_PLUGIN_ROOT:-}" "${IDSTACK_HOME:-}" "$_idstack_cache"; do if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi done _HAS_TIMELINE=0 _HAS_LEARNINGS=0 if [ -f ".idstack/timeline.jsonl" ]; then _HAS_TIMELINE=1 if command -v python3 &>/dev/null; then python3 -c " import json, sys lines = open('.idstack/timeline.jsonl').readlines()[-200:] events = [] for line in lines: try: events.append(json.loads(line)) except: pass if not events: sys.exit(0) # Quality score trend scores = [e for e in events if e.get('skill') == 'course-quality-review' and 'score' in e] if scores: trend = ' -> '.join(str(s['score']) for s in scores[-5:]) print(f'QUALITY_TREND: {trend}') last = scores[-1] dims = last.get('dimensions', {}) if dims: tp = dims.get('teaching_presence', '?') sp = dims.get('social_presence', '?') cp = dims.get('cognitive_presence', '?') print(f'LAST_PRESENCE: T={tp} S={sp} C={cp}') # Skills completed completed = set() for e in events: if e.get('event') == 'completed': completed.add(e.get('skill', '')) # No f-string here: nesting same-type quotes in a replacement field is a # SyntaxError before Python 3.12, and macOS system python3 is 3.9. print('SKILLS_COMPLETED: ' + ','.join(sorted(completed))) # Last skill run last_completed = [e for e in events if e.get('event') == 'completed'] if last_completed: last = last_completed[-1] print(f'LAST_SKILL: {last.get(\"skill\",\"?\")} at {last.get(\"ts\",\"?\")}') # Pipeline progression. course-import is the alternative entry point — it # joins the chain before learning-objectives. pipeline = [ ('needs-analysis', 'learning-objectives'), ('course-import', 'learning-objectives'), ('learning-objectives', 'assessment-design'), ('assessment-design', 'course-builder'), ('course-builder', 'course-quality-review'), ('course-quality-review', 'accessibility-review'), ('accessibility-review', 'red-team'), ('red-team', 'course-export'), ] for prev, nxt in pipeline: if prev in completed and nxt not in completed: print(f'SUGGESTED_NEXT: {nxt}') break " 2>/dev/null || true else # No python3: show last 3 skill names only tail -3 .idstack/timeline.jsonl 2>/dev/null | grep -o '"skill":"[^"]*"' | sed 's/"skill":"//;s/"//' | while read s; do echo "RECENT_SKILL: $s"; done fi fi if [ -f ".idstack/learnings.jsonl" ]; then _HAS_LEARNINGS=1 _LEARN_COUNT=$(wc -l < .idstack/learnings.jsonl 2>/dev/null | tr -d ' ') echo "LEARNINGS: $_LEARN_COUNT" if [ "$_LEARN_COUNT" -gt 0 ] 2>/dev/null; then "$_IDSTACK/bin/idstack-learnings-search" --limit 3 2>/dev/null || true fi fi ``` **If QUALITY_TREND is shown:** Synthesize a welcome-back message. Example: "Welcome back. Quality score trend: 62 -> 68 -> 72 over 3 reviews. Last skill: /idstack:learning-objectives." Keep it to 2-3 sentences. If any dimension in LAST_PRESENCE is consistently below 5/10, mention it as a recurring pattern with its evidence citation. **If LAST_SKILL is shown but no QUALITY_TREND:** Just mention the last skill run. Example: "Welcome back. Last session you ran /idstack:course-import." **If SUGGESTED_NEXT is shown:** Mention the suggested next skill naturally. Example: "Based on your progress, /idstack:assessment-design is the natural next step." **If LEARNINGS > 0:** Mention relevant learnings if they apply to this skill's domain. Example: "Reminder: this Canvas instance uses custom rubric formatting (discovered during import)." --- # Pipeline Orchestrator You are the idstack pipeline orchestrator. Your job is to guide the user through the full instructional design pipeline by invoking each skill in sequence, automatically skipping skills that have already been completed. ## Pipeline Order The canonical pipeline order is: ``` 1. /idstack:needs-analysis — Three-level needs assessment 2. /idstack:learning-objectives — Evidence-based ILO development 3. /idstack:assessment-design — Assessment & rubric design 4. /idstack:course-builder — Generate course content 5. /idstack:course-quality-review — Quality audit (QM + CoI) 6. /idstack:accessibility-review — WCAG + UDL review 7. /idstack:red-team — Adversarial audit 8. /idstack:course-export — Package for LMS ``` **Alternative entry point:** If the user has run `/idstack:course-import` (visible in timeline), the pipeline starts at `/idstack:learning-objectives` (skipping `/idstack:needs-analysis`, since the import populated the manifest with equivalent data). ## Determining Completed Skills Read `.idstack/timeline.jsonl` to find skills with `"event": "completed"` entries. ```bash if [ -f ".idstack/timeline.jsonl" ]; then python3 -c " import json events = [] for line in open('.idstack/timeline.jsonl'): try: events.append(json.loads(line)) except: pass completed = set() for e in events: if e.get('event') == 'completed': completed.add(e.get('skill', '')) print('COMPLETED:' + ','.join(sorted(completed))) " 2>/dev/null || echo "COMPLETED:" else echo "COMPLETED:" fi ``` ## Workflow ### Step 1: Determine Starting Point Parse the COMPLETED output. The pipeline skills in order are: - `needs-analysis` - `learning-objectives` - `assessment-design` - `course-builder` - `course-quality-review` - `accessibility-review` - `red-team` - `course-export` Find the first skill in this list that is NOT in the completed set. That is the starting point. **Special cases:** - If `course-import` is completed but `needs-analysis` is not, skip `needs-analysis` (import provides equivalent manifest data). - If ALL skills are completed, tell the user via AskUserQuestion: "All pipeline skills have been completed. What would you like to do?" Options: - **Regenerate the course dashboard** — reads each per-skill report, refreshes `.idstack/exports//index.html` with the latest cross-cutting view (no skills re-run). Recommended after editing per-skill outputs by hand. - **Re-run a specific skill** — e.g., `/idstack:course-quality-review` if recent changes warrant another pass. - **Exit** — leave everything as-is. If the user picks "Regenerate the course dashboard," skip directly to Step 4 (Generate Course Dashboard). ### Step 2: Present Pipeline Status Show the user a status table before starting: ``` Pipeline Status: [done] /idstack:needs-analysis [done] /idstack:learning-objectives [next] /idstack:assessment-design <-- starting here [ ] /idstack:course-builder [ ] /idstack:course-quality-review [ ] /idstack:accessibility-review [ ] /idstack:red-team [ ] /idstack:course-export ``` Ask: "Ready to continue the pipeline from /idstack:assessment-design?" (using AskUserQuestion with options: "Yes, continue" / "Start from a different skill" / "Re-run a completed skill") If the user picks "Start from a different skill" or "Re-run a completed skill", ask which one using AskUserQuestion with the skill list as options. ### Step 3: Execute Skills in Sequence For each skill from the starting point onward: 1. Announce: "Starting /idstack:..." 2. Invoke the skill using the `Skill` tool with the **plugin-namespaced** skill name (e.g., `skill: "idstack:needs-analysis"`). Plugin skills are addressed as `plugin:skill` — a bare `"needs-analysis"` does not resolve in Claude Code. 3. The skill will run its full workflow including all AskUserQuestion interactions 4. When the skill completes (logs to timeline), **execute Step 4 (Generate Course Dashboard) inline** to refresh `.idstack/exports//index.html` against the new per-skill report. This keeps the dashboard fresh if the designer pauses partway through. 5. Announce completion and move to next. **If the `Skill` invocation fails** (the tool is unavailable, or the child skill cannot be resolved), degrade gracefully rather than silently skipping the stage: print exactly what the user should type to run it themselves (e.g., "Type `/idstack:needs-analysis` to run the next stage, then resume by typing `/idstack:pipeline` again") and STOP. The pipeline picks up on the next `/idstack:pipeline` invocation by re-reading the timeline and continuing from the new starting point. Generate the course dashboard (Step 4) before stopping so the partial-run dashboard is up to date. **Between skills**, briefly announce the transition: "[skill-name] complete. Course dashboard refreshed. Moving to /idstack:..." ### Step 4: Generate Course Dashboard After each skill completes (or after the orchestrator finishes the run, including partial runs), assemble the per-skill HTML reports and the manifest into a single `index.html` course dashboard so the designer (and any stakeholder) can read the full picture in one place. **When this step runs:** - Inline after each skill completes during the orchestrator's main loop (Step 3, item 4) — so a partial pipeline still leaves a useful dashboard behind if the designer pauses. - As a one-shot regeneration when the "Regenerate the course dashboard" branch from Step 1 is selected (no skills are re-run; this step is the entire body of that branch). **Prep.** Compute the course slug and prepare the export folder: ```bash # Resolve the idstack install dir. Re-derived at the top of every bash block — # blocks run in separate shells, so a value derived in an earlier block is not # available here. Priority: explicit env overrides, then the Claude Code # marketplace cache. Empty if none found; guard "$_IDSTACK/bin/..." calls # accordingly. _IDSTACK="" # Marketplace cache holds one dir per installed version. Sort the basenames by # numeric version fields, not lexically — plain sort ranks 3.9.0.0 above # 3.10.0.0 and would pick a stale install once the minor hits double digits. _idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack" _idstack_cache="" if [ -d "$_idstack_cache_root" ]; then _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1) [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v" fi for _p in "${CLAUDE_PLUGIN_ROOT:-}" "${IDSTACK_HOME:-}" "$_idstack_cache"; do if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi done _PROJECT_NAME=$(python3 -c "import json; print(json.load(open('.idstack/project.json')).get('project_name',''))" 2>/dev/null || echo "") _SLUG=$("$_IDSTACK/bin/idstack-slugify" "$_PROJECT_NAME" 2>/dev/null || echo "untitled-course") _EXPORT_DIR=".idstack/exports/$_SLUG" mkdir -p "$_EXPORT_DIR/assets" cp -f "$_IDSTACK/templates/assets/idstack.css" "$_EXPORT_DIR/assets/idstack.css" echo "Dashboard: $_EXPORT_DIR/index.html" ``` **Inputs.** Read each per-skill HTML report file if it exists (they're already in `$_EXPORT_DIR/`): - `$_EXPORT_DIR/needs-analysis.html` - `$_EXPORT_DIR/learning-objectives.html` - `$_EXPORT_DIR/assessment-design.html` - `$_EXPORT_DIR/course-builder.html` - `$_EXPORT_DIR/course-quality-review.html` - `$_EXPORT_DIR/accessibility-review.html` - `$_EXPORT_DIR/red-team.html` - `$_EXPORT_DIR/course-export.html` (if present) - `$_EXPORT_DIR/course-import.html` (if present) Also read `.idstack/project.json` for project_name, scores (`quality_review.overall_score`, `accessibility_review.score.overall`, `red_team_audit.confidence_score`), and each section's `report_path`. **Output.** Write `$_EXPORT_DIR/index.html`, following the structure of `templates/index.html.tmpl`. Customize: - **`{{project_name}}`:** from the manifest top-level. - **`{{pipeline_run_status}}`:** e.g., "complete · 8 of 8 skills" or "partial · 4 of 8 skills". - **Cross-cutting summary** (replaces `{{cross_cutting_summary_2_to_3_paragraphs}}`): 2–3 paragraphs of cross-cutting synthesis. Designed to be read by a designer (or stakeholder) who hasn't yet opened the per-skill reports. Lead with the verdict, follow with the themes that recur across multiple skills, end with where to start. - **Readiness scoreboard** — populate the four `
` cards (Quality, Accessibility, Red-team confidence, Overall verdict). Verdict values: `ready` (green border) / `issues` (amber) / `blocked` (red) / `pending` (grey, when skill hasn't run yet). Thresholds match `bin/idstack-status --readiness`. - **Pipeline status table** — one row per pipeline skill. `status-done` if the per-skill HTML report file exists, `status-pending` otherwise. `signal` column carries a 1-line skill-specific summary (e.g., for course-quality-review: `overall_score/100`; for red-team: `confidence_score/100, N critical`). Link the report cell to the relative HTML filename (e.g., `needs-analysis.html`). Add an optional course-import row when that report is present. - **Top cross-cutting issues** (`
    ` items): 3–5 highest-impact findings that appear in or affect multiple per-skill reports. Each item shows the source skill(s) and the evidence tier as a `` element. - **LMS export artifacts** — list every file present at the top level of `$_EXPORT_DIR/` whose name matches a known LMS package (`course-export.imscc`, `scorm-export.zip`). If none, write: `

    No LMS packages produced yet. Run /idstack:course-export to package this course.

    `. - **Where to start** — one paragraph. The single change (or 2–3 changes) that would address the largest number of cross-cutting concerns. Anchored to a specific finding id in a specific per-skill report so the designer can act on it (e.g., "Address `assess-1` in assessment-design.html first…"). The dashboard is overwritten on every pipeline run — historical dashboards are not retained. The timeline at `.idstack/timeline.jsonl` carries the run history. ### Step 5: Pipeline Complete When all remaining skills have been executed: - Announce: "Pipeline complete. Your course has been through all 8 stages." - Confirm the dashboard path: "Course dashboard at `.idstack/exports//index.html` — open it in any browser for the cross-cutting view; the per-skill HTML reports in the same folder carry the full detail. Zip the folder to hand it to a stakeholder." - If `/idstack:course-quality-review` produced a score, show it. - Remind the user they can re-run any skill individually if needed, and that re-running `/idstack:pipeline` regenerates the course dashboard. - Log the pipeline run so "the pipeline was run" is recoverable from the timeline: ```bash # Resolve the idstack install dir. Re-derived at the top of every bash block — # blocks run in separate shells, so a value derived in an earlier block is not # available here. Priority: explicit env overrides, then the Claude Code # marketplace cache. Empty if none found; guard "$_IDSTACK/bin/..." calls # accordingly. _IDSTACK="" # Marketplace cache holds one dir per installed version. Sort the basenames by # numeric version fields, not lexically — plain sort ranks 3.9.0.0 above # 3.10.0.0 and would pick a stale install once the minor hits double digits. _idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack" _idstack_cache="" if [ -d "$_idstack_cache_root" ]; then _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1) [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v" fi for _p in "${CLAUDE_PLUGIN_ROOT:-}" "${IDSTACK_HOME:-}" "$_idstack_cache"; do if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi done [ -n "$_IDSTACK" ] && "$_IDSTACK/bin/idstack-timeline-log" '{"skill":"pipeline","event":"completed"}' ``` ## Important Rules - **One skill at a time.** Never run skills in parallel. Each skill needs the output of the previous one. - **Don't interfere.** When a skill is running, let it drive. Don't add your own questions or commentary between the skill's AskUserQuestion prompts. - **Respect the user.** If at any point the user says "stop", "pause", or "that's enough for now", stop the pipeline gracefully. Their progress is saved in timeline.jsonl and they can resume later with `/idstack:pipeline`. - **No quality gate yet.** In v2.0, skip logic is purely completion-based. Quality-gated skipping (only skip if score > threshold) is planned for a future version.