Review a completed task for reusable lessons when the user requests reflection or workflow improvements.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Reflect
Identify demonstrated workflow problems and useful lessons from the requested task. A correction, failure, or long conversation does not automatically require reflection or new persistent rules.
Use the current conversation when sufficient. If older evidence is needed, resolve `../recall/scripts/find-transcripts.mjs` relative to this skill and run it with `node`, `--host claude`, `--workspace` set to this workspace, and a bounded `--limit`. Do not scan unrelated projects' transcripts.
Review directly for a narrow lesson. For a complex task, independent judgment, tooling, or divergent reviews may help; load only the corresponding [judgment](references/judgment-reviewer.md), [tooling](references/tooling-reviewer.md), or [divergent](references/divergent-reviewer.md) template. The parent can synthesize without another agent.
Prefer a correction to an existing rule over a new skill. Add a script, lint rule, or check only when it reliably prevents a recurring problem at reasonable maintenance cost. Do not generalize a one-off into a universal policy.
…
The line at the top of this page pins the label git:20260907.b1269d9, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (1646 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
shiwenbin1617/pstack · 4 stars · license a license file GitHub does not identify · pushed 2026-09-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7ahcfmrq3qqc3mle
GET https://markdownregistry.com/api/v1/resolve?ref=shiwenbin1617/pstack/reflect
GET https://markdownregistry.com/api/v1/blob/801a9b58a0b0a867863ea04310d67e4fb1224e347ca546ed3e5c55931209db4d
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
shiwenbin1617/pstack · adapters/claude-code/overrides/setup-pstack/SKILL.md · Configure which Claude Code models pstack uses per role. Use for /setup-pstack or requests to change pstack model…
shiwenbin1617/pstack · adapters/codex/overrides/setup-pstack/SKILL.md · Configure optional per-role model preferences for pstack on Codex. Use for $setup-pstack or requests to change pstack…
shiwenbin1617/pstack · automations/benny/skills/reproduce-and-fix-issues/SKILL.md · Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft…
shiwenbin1617/pstack · automations/benny/skills/setup-benny/SKILL.md · Configure Benny and prepare its triage and repro automations. Use when installing Benny or changing its Slack, tracker…
shiwenbin1617/pstack · skills/architect/SKILL.md · Design types, interfaces, and module ownership for a requested architectural change or an unresolved design choice.
shiwenbin1617/pstack · skills/arena/SKILL.md · Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for…
shiwenbin1617/pstack · skills/automate-me/SKILL.md · Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a…
shiwenbin1617/pstack · skills/blast-radius/SKILL.md · Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe…
shiwenbin1617/pstack · skills/create-verification-skill/SKILL.md · Generate a project-local verification skill that drives your app the way a user does — any language, framework, or…
cursor/plugins · pstack/skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
cursor/plugins · harness/pstack/claude-code/skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
nightly-labs/openbot · marketplace/production-catalog/bundles/pstack/skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
michael-denyer/pstack-claude · plugins/pstack/skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
backnotprop/pstack · skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
bradygaster/squad · packages/squad-cli/templates/skills/reflect/SKILL.md · Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating…
bradygaster/squad · packages/squad-sdk/templates/skills/reflect/SKILL.md · Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating…
bradygaster/squad · .squad-templates/skills/reflect/SKILL.md · Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating…