survey-corps SKILL.md skillA
survey-corps from ljferrer/workauditrefine is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ljferrer/workauditrefine/survey-corps@git:20261030.b0f6babPins git:20261030.b0f6bab in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ljferrer/workauditrefine
- Path
skills/survey-corps/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261030.b0f6bab, committed Oct 30, 2026
- First version recorded
- Aug 5, 2026
- Size
- 12,280 bytes
- Repository stars
- 11
- License
- MIT
Survey this repo's memory lessons and open GitHub issues into war-shaped design specs — first mine qualifying hot lessons from both memory roots into real memory-mined issues (redaction-lint-guarded, slug-deduped across open + closed), then sweep the backlog (run-bookkeeping labels dropped, war-followup debt first-class), fan out reader agents per issue, cluster the summaries into coherent groups, synthesize one spec per group via the /war-strategy spec template, then verify every swept issue…
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
# /survey-corps — memories + issues → specs
You are the **Survey Corps**. You first **mine** qualifying memory lessons into real issues, then
sweep the repo's open issues, cluster them into coherent groups, and author one war-shaped design
spec per group — every swept issue accounted for, nothing committed. The next pipeline step is
`/war-machine` (specs → plans + roadmap); you hand off via the survey manifest below.
This skill authorizes the **Workflow tool** (precedent: `/red-team`, `/lessons-learned`): the
reader fan-out, the cluster barrier, and the per-group spec synthesis run as a Workflow.
**Seat models.** Resolve the run config before the first spawn: `node ${CLAUDE_PLUGIN_ROOT}/skills/war/assets/war-config.mjs <repo>/.claude/war/config.json --fill-defaults`, or `--preset balanced` when that file is missing. On a zero exit, give every `agent()` its seat's `model`, plus `effort` unless it is `default`, from `agents.survey`: `miner` classifies lessons (Step 0), `reader` summarizes issues (Step 2), `cluster` groups them (Step 3), `synth` writes each spec (Step 4), and `critic` runs the completeness check (Step 5). On a nonzero exit, omit both and the agents inherit the…
…Read the whole file at its exact version.
How to install
mdr add ljferrer/workauditrefine/survey-corps@sha256:4e8eae529aefa9f5The line at the top of this page pins the label git:20261030.b0f6bab, 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.
[](https://markdownregistry.com/a/art_3acogb64ynvqklhs)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 5, 2026 and Oct 30, 2026, about one every 22 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261030.b0f6bab latest | 2026-10-30 | b0f6bab | 12,280 B | A | view · diff |
| git:20261030.e0512aa | 2026-10-30 | e0512aa | 12,280 B | A | view · diff |
| git:20260825.e1a39df | 2026-08-25 | e1a39df | 11,440 B | A | view · diff |
| git:20260825.fe4bb36 | 2026-08-25 | fe4bb36 | 11,600 B | A | view · diff |
| git:20260805.871f721 | 2026-08-05 | 871f721 | 10,757 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (12280 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
ljferrer/workauditrefine · 11 stars · license MIT · pushed 2026-11-04 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_3acogb64ynvqklhs GET https://markdownregistry.com/api/v1/resolve?ref=ljferrer/workauditrefine/survey-corps GET https://markdownregistry.com/api/v1/blob/4e8eae529aefa9f50723b22cf62c0d595be22a77df6e0c334b19a606e2952704
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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.