fix
Polymorphic iterative repair loop — accept a verifier failure, structured findings (review/resolve/triage-issue), or a bug description; modify→verify→keep on…
Skill by OutlineDriven
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/outlinedriven-fix-eec460
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops, security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/fix
What's inside
- Skill name
fix- Description
- Polymorphic iterative repair loop — accept a verifier failure, structured findings (review/resolve/triage-issue), or a bug description; modify→verify→keep on green, auto-revert on guard regression, until clean or iteration cap. Use when the user says "fix", "make it pass", or "apply the findings", or hands an artifact + repo and expects patches; auto-routes to gh-fix-ci or gh-address-comments when an open PR + gh auth + GH-flavored input is detected.
- License
- Apache-2.0
- Metadata
- short-description: Iterative fix loop with auto-revert
- Instructions
- 126 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- classifier.md · references/
- loop.md · references/
- verifiers.md · references/
SKILL.md (first lines)
# Fix Failure-driven iterative repair. Detect → Prioritize → Fix ONE thing → Commit → Verify → Keep/Revert → Repeat. ## When to Apply / NOT **Apply:** user says "fix", "make it pass", "apply findings"; input is a verifier failure, findings file, or bug description. **NOT apply:** - CI/PR workflows with no local context → use `gh-fix-ci` - PR review comments → use `gh-address-comments` - Merge conflicts - Analysis-only tasks → use `resolve` or `debug` - Planned change without a failure driver → use `proceed` ## Detected Mode Acknowledgement [LOAD-BEARING] First output line before ANY edit: ``` detected: <mode> — target=TARGET guard=GUARD scope=SCOPE cap=20 ``` Mode values: `gh-route`, `findings`, `verifier-failure`, `bug-spec`. Full classifier: `references/classifier.md`. ## Input Classifier First-match wins. Full detail: `references/classifier.md`. | Priority | Mode | Minimum condition | |----------|------|-------------------| | 1 | `gh-route` | GH-flavored input + open PR + `gh auth status` clean | | 2 | `findings` | Path to `*/findings.md`, `*/review/*.md`, or structured findings text | | 3 | `verifier-failure` | Raw verifier stdout (`FAILED`, `error TS`, `--- FAIL`, etc.) | | 4 | `bug-spec` | Natural-language description — catch-all fallback | ## Auto-Detect Gate Auto-infer: target verifier, scope glob, guard command, iteration cap (default 20). Trigger `AskUserQuestion` (single-select per axis, NEVER `multiSelect`) when: - `MIXED_MODE`: findings artifact AND verifier-failure output both present - `GH_PARTIAL`: GH-flavored input but no open PR, or `gh auth status` fails - `LANG_UNKNOWN`: verifier-failure detected but verifier undetectable - `SCOPE_AMBIGUOUS`: bug-spec with no module, file, or component reference ## Iterative Loop Full spec: `references/loop.md`. Key rules: - One fix per iteration. Apply fix → stage checkpoint commit → run verifiers → **KEEP** on green, revert with `git revert HEAD --no-edit` on red. A commit is *kept* only when the guard passes. - Decide matrix: - `delta > 0` + guard ok → **KEEP** - `delta > 0` + guard fail → **REWORK** (max 2 reworks per item; 4th attempt → SKIP) - `delta ≤ 0` → **DISCARD** — revert immediately - 3 total skips → **HALT** with summary - Revert: always `git revert HEAD --no-edit`. Never `reset --hard`. - Cap: 20 iterations default. Print progress every 5 iterations. - Refuse loop on protected branches (`main`, `master`, `release/*`). - Override: `iterations: N` or `--iterations N` in invocation. ## Verifier Detection Repo-native first (use `fd --max-depth 2` to locate): 1. `Justfile` → `just test` (guard: `just check`) 2. `Makefile` → `make test` (guard: `make check`) 3. `package.json` → `npm test` (guard: `tsc --noEmit && eslint .`) 4. `dune-project` → `dune build @runtest` (guard: `dune build`) Language fallbacks: - Python: `pytest` + `ruff check . && mypy .` - TypeScript: `vitest run` + `tsc --noEmit && eslint .` - Rust: `cargo test` + `cargo clippy -- -D warnings` - Go: `go test ./...` + `golangci-lint run` - OCaml: `dune build @runtest` + `dune build` Full matrix: `references/verifiers.md`. ## GH Auto-Route When open PR + `gh auth status` clean + GH-flavored input: | Sub-target | Trigger language | |------------|-----------------| | `gh-fix-ci` | "CI", "Actions", "workflow", "checks", Actions run URL | | `gh-address-comments` | "reviewer said", "address comment", "PR feedback", "requested changes" | Both sets of language → fire `AMBIGUOUS_GH_ROUTE` (single-select: `gh-fix-ci` vs `gh-address-comments`). Partial match → `GH_PARTIAL` ambiguity flag. ## Hand-off & Integration - `debug` upstream: unclear root cause — debug findings become the fix target. - `triage-issue` upstream: bug-spec mode — triage produces repro + TDD plan first. - `test-driven` partner: failing test ↔ green flip; delegate RED→GREEN cycle. - `proceed` complement: planned change without failure → `proceed`; failure-driven → `fix`. - `resolve` / `review` / `triage-issue` as findings sources: their output paths feed findings mode. ## Failure Modes - No verifier output: emit warning, raise `LANG_UNKNOWN`. - 3 strikes on one item: SKIP, add to `blocked.md`, recommend `debug`. - 3 total skips: HALT with session summary. - Guard ambiguous: `AskUserQuestion` for guard command. - Mixed-mode input: raise `MIXED_MODE`. - Protected branch: REFUSE with message before entering loop. ## Anti-Patterns - Never `@ts-ignore` / `# type: ignore` / `// eslint-disable` to silence errors. - Never delete tests to make them pass. - ONE fix per iteration — no "while I'm here" changes. - No `git reset --hard`. - Recursion guard: `--mode <X>` bypasses classifier entirely; `gh-fix-ci` re-entering as `fix --mode verifier-failure` cannot loop back into `gh-fix-ci`. ## Constitutional Rules
From OutlineDriven/odin-codex-plugin, Apache-2.0.
More from OutlineDriven/odin-codex-plugin
- 0.525score
improve-codebase-architecture
OutlineDriven
Surface deepening refactors that turn shallow modules into deep ones, informed by `CONTEXT.md` and `docs/adr/`.
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
proof-driven
OutlineDriven
Proof-driven development.
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
domain-model
OutlineDriven
Grill against the existing domain model.
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
git-branchless
OutlineDriven
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via `git move`, event-log recovery via `git…
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
memory-update
OutlineDriven
Scan agent's session-history transcripts for save-worthy signals (corrections, preferences, decisions, references), propose and write auto-memory files with…
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
memory-sanitize
OutlineDriven
Produce share-safe copies of memory files under /tmp with PII redacted (paths, emails, session IDs, dates) and credentials scanned (tokens, keys); never…
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
cleanup-codebase
OutlineDriven
Reduce concepts, duplication, and ceremony in internal code while touching nearby code.
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
design-by-contract
OutlineDriven
Design-by-Contract (DbC) development.
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
gh-fix-ci
OutlineDriven
Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize the failure, then plan and implement the fix after user approval.
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
design
OutlineDriven
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code.
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
memory-clean
OutlineDriven
Audit memory directory for structural issues (orphans, dangling refs, duplicates, missing sections, oversized entries) and staleness against session-history…
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
setup-gitignore
OutlineDriven
Initialize or idempotently revise the repo's .gitignore by composing gitignore.io templates, AI-tooling/IDE patterns, and confirmed noise from git status.
SkillCFreshness: C★ 14Claude Code +9
Signals
- Stars
- 14
- Forks
- 2
- Open issues
- 2
- Last commit (this folder)
- May 11, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Website
- outlinedriven.github.io
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from OutlineDriven
- 0.525score
design-by-contract
OutlineDriven
Design-by-Contract (DbC) development.
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
gh-fix-ci
OutlineDriven
Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize the failure, then plan and implement the fix after user approval.
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
cleanup-codebase
OutlineDriven
Reduce concepts, duplication, and ceremony in internal code while touching nearby code.
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
design
OutlineDriven
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code.
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
domain-model
OutlineDriven
Grill against the existing domain model.
SkillCFreshness: C★ 14Claude Code +9 - 0.525score
git-branchless
OutlineDriven
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via `git move`, event-log recovery via `git…
SkillCFreshness: C★ 14Claude Code +9
Cite this page
fix skill. Agent Mart. https://agentmart.dev/skills/outlinedriven-fix-eec460 (last updated 2026-10-24)