recovery-classification SKILL.md skillA

recovery-classification from naimkatiman/continuous-improvement is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add naimkatiman/continuous-improvement/recovery-classification@git:20260517.966ce51

Pins git:20260517.966ce51 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
naimkatiman/continuous-improvement
Path
plugins/continuous-improvement/skills/recovery-classification/SKILL.md
Versions recorded
2
Latest version
git:20260517.966ce51, committed May 17, 2026
First version recorded
May 9, 2026
Size
4,799 bytes
Repository stars
9
License
MIT

Enforces Law 4 (Verify Before Reporting) of the 7 Laws of AI Agent Discipline. After any failure in the verification ladder or auto-loop, classify the failure class before retrying — provider, tool-schema, deterministic-policy, git, worktree, runtime — so retry-vs-pause-vs-self-heal-vs-stop is an intentional decision, not a generic 'try again'.

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

# Recovery Classification Skill

When a phase or unit fails, name the failure class first. Generic "retry on failure" hides repeatable failure modes and turns them into flaky tests.

## When to Use

- After any Phase 1–6 failure in `verification-loop`.
- After any auto-loop unit that exits non-zero.
- After any tool call the harness rejects (schema validation, policy gate, deterministic block).
- Before re-running anything that just failed — classification fires once, before the first retry.

## Why This Skill Exists

GSD-2's [CONTEXT.md](https://github.com/gsd-build/gsd-2/blob/main/CONTEXT.md) names "Recovery Classification" as one of four runtime invariant modules. Common failure modes it catches:

- **Deterministic-policy blocks misclassified as generic provider failures** — gateguard denials retried in a loop until budget is exhausted.
- **Schema-validation failures retried verbatim** — wasting tokens on a call the validator will keep rejecting.
- **Stale-worker / stale-lock states** — no retry can resolve a worker that died holding a lock; the loop just spins.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add naimkatiman/continuous-improvement/recovery-classification@sha256:9e66e748bd08a087

The line at the top of this page pins the label git:20260517.966ce51, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7bskhzww2lt43xpq.svg)](https://markdownregistry.com/a/art_7bskhzww2lt43xpq)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between May 9, 2026 and May 17, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
git:20260517.966ce51 latest2026-05-17 966ce51 4,799 BA view · diff
git:20260509.0df8c0f2026-05-09 0df8c0f 4,777 BA view

Audit of the latest version

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 (4799 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

naimkatiman/continuous-improvement · 9 stars · license MIT · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7bskhzww2lt43xpq
GET https://markdownregistry.com/api/v1/resolve?ref=naimkatiman/continuous-improvement/recovery-classification
GET https://markdownregistry.com/api/v1/blob/9e66e748bd08a0877c546cf3a71899795af840826c574fef7d6c2e52301c62c6

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.

More from naimkatiman/continuous-improvement

AGENTS.md AGENTS.md file
naimkatiman/continuous-improvement · AGENTS.md
git:20260906.e54b2e4 · audit A · 9 stars
CLAUDE.md CLAUDE.md file
naimkatiman/continuous-improvement · CLAUDE.md
git:20260906.e54b2e4 · audit A · 9 stars
continuous-improvement SKILL.md skill
naimkatiman/continuous-improvement · SKILL.md · Install structured self-improvement loops with instinct-based learning into Claude Code — research, plan, execute…
git:20260906.3e80e82 · audit A · 9 stars
llms.txt llms.txt file
naimkatiman/continuous-improvement · llms.txt
git:20260906.fca30a4 · audit A · 9 stars
audit SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/audit/SKILL.md · Enforces Law 4 (Verify Before Reporting) of the 7 Laws of AI Agent Discipline. Audits a window of recent commits for…
git:20260602.e0e1217 · audit A · 9 stars
continuous-improvement SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/continuous-improvement/SKILL.md · Install structured self-improvement loops with instinct-based learning into Claude Code — research, plan, execute…
git:20260906.3e80e82 · audit A · 9 stars
deploy-receipt SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/deploy-receipt/SKILL.md · Enforces Law 4 (Verify Before Reporting) of the 7 Laws of AI Agent Discipline at the deploy seam. A merge into a branch…
git:20260906.fca30a4 · audit A · 9 stars
gateguard SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/gateguard/SKILL.md · Enforces Law 1 (Research Before Executing) of the 7 Laws of AI Agent Discipline. Fact-forcing gate that blocks…
git:20261101.d6fb48b · audit A · 9 stars
goal-monitor SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/goal-monitor/SKILL.md · Enforces Law 2 (Plan Is Sacred) of the 7 Laws of AI Agent Discipline. Detects when a session has drifted away from its…
git:20260610.57b1c8e · audit A · 9 stars
grill-me SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/grill-me/SKILL.md · Enforces Law 1 (Research Before Executing) of the 7 Laws of AI Agent Discipline. Interview the user relentlessly about…
git:20260511.2223960 · audit A · 9 stars
grill-with-docs SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/grill-with-docs/SKILL.md · Enforces Law 1 (Research Before Executing) and Law 7 (Learn From Every Session) of the 7 Laws of AI Agent Discipline…
git:20260527.d97abe8 · audit A · 9 stars
handoff SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/handoff/SKILL.md · Enforces Law 5 (Reflect After Every Session) of the 7 Laws of AI Agent Discipline. Compact the current conversation…
git:20260610.57b1c8e · audit A · 9 stars

Every file in naimkatiman/continuous-improvement

Browse by kind, by grade A, or by owner.