retry-fix
Investigate recurring bugs and regression cycles before attempting another fix. Use when: (1) User says 'still broken', 'X is blue again', 'this is the second/third/fourth time', 'we tried this before', 'I'm doing this many times', 'the regression is back', 'didn't stick', (2) A bug has been 'fixed' before but came back, (3) User mentions doing the same fix again, (4) Code changed for a feature but the previous fix got overwritten. ALWAYS use this skill before writing any code when a regression is detected — surface the prior-attempts table and get explicit confirmation before proceeding.
Best use case
retry-fix is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Investigate recurring bugs and regression cycles before attempting another fix. Use when: (1) User says 'still broken', 'X is blue again', 'this is the second/third/fourth time', 'we tried this before', 'I'm doing this many times', 'the regression is back', 'didn't stick', (2) A bug has been 'fixed' before but came back, (3) User mentions doing the same fix again, (4) Code changed for a feature but the previous fix got overwritten. ALWAYS use this skill before writing any code when a regression is detected — surface the prior-attempts table and get explicit confirmation before proceeding.
Teams using retry-fix should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/retry-fix/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How retry-fix Compares
| Feature / Agent | retry-fix | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Investigate recurring bugs and regression cycles before attempting another fix. Use when: (1) User says 'still broken', 'X is blue again', 'this is the second/third/fourth time', 'we tried this before', 'I'm doing this many times', 'the regression is back', 'didn't stick', (2) A bug has been 'fixed' before but came back, (3) User mentions doing the same fix again, (4) Code changed for a feature but the previous fix got overwritten. ALWAYS use this skill before writing any code when a regression is detected — surface the prior-attempts table and get explicit confirmation before proceeding.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Retry Fix A recurring bug has been patched before and regressed. This skill excavates all prior attempts, diagnoses the structural pattern that lets it regress, and gates any new code change behind explicit user confirmation. **Argument:** `$ARGUMENTS` — a problem slug (e.g. `active-frame-border`, `zoom-transform`, `modal-focus`). ## Step 1: Gather prior attempts Run these searches in parallel. Use the slug and obvious keyword variants (kebab → spaces, camelCase, partial words): ```bash # Git commits git log --all --oneline -i --grep="<slug-keyword-1>" git log --all --oneline -i --grep="<slug-keyword-2>" # variant if needed # Closed GitHub issues gh issue list --state closed --search "<slug keywords>" --limit 30 ``` For each result: record SHA (or issue number), date, and title. Deduplicate overlapping hits. ## Step 2: Read each prior attempt For each unique commit SHA found: ```bash git show <sha> --stat # what files changed git show <sha> # full diff (skim for the structural change) ``` For each closed issue number: read the issue body (use `/gh-fetch-issue` if it has attached images). Capture: - What the author thought was wrong - What code changed - What was NOT changed (the thing that caused the regression) ## Step 3: Check for existing lessons file Look for a project-scoped lessons skill matching the slug: ```bash ls .claude/skills/ | grep "l-lessons" ``` If `.claude/skills/l-lessons-<slug>/SKILL.md` exists: - Read it fully - Check the `last-updated:` frontmatter field - If older than 90 days: surface a warning — "Lessons file may be out of date (last updated: YYYY-MM-DD). Verify context still applies." ## Step 4: Emit the structured report Produce the following sections **in this exact order**. Do not skip sections. Do not merge sections. --- ### 1. Prior Attempts Table | # | Date | Commit SHA | Issue | What it changed | What it missed | |---|------|-----------|-------|-----------------|----------------| | 1 | YYYY-MM-DD | `abc1234` | #N | One-line description | What was left untouched | | 2 | … | … | … | … | … | One row per distinct fix attempt. If a commit and an issue describe the same attempt, merge into one row. ### 2. Why Each Attempt Failed One paragraph per attempt (numbered to match the table). Name the **specific assumption that was wrong** — not the symptom. Example: "Attempt 1 changed the JS default but not the CSS fallback, assuming CSS consumed the JS value at runtime. In fact the CSS fallback fires before JS runs, so the old palette index was visible until settings loaded." ### 3. Structural Diagnosis Answer this question: **What is the architectural pattern that lets this bug regress?** Concrete examples of structural diagnoses: - "Multiple sources of truth for the same value; patches fix one site and miss others" - "The fix lives in an ephemeral layer (JS runtime) that is overwritten by a persistent layer (CSS fallback) on each cold boot" - "No test owns this invariant; regressions are invisible until a human notices visually" One or two paragraphs. Specific over general. ### 4. Next-Step Checklist Bulleted requirements the next attempt MUST include to prevent regression: - [ ] Single source of truth — name the file:line that will own the value - [ ] Guard test — describe the test (unit/e2e/visual) that will fail if the bug regresses - [ ] Lint / static rule — if applicable, a grep pattern or ESLint rule that prevents the bad pattern - [ ] Test matrix — list all states/paths that must be verified (e.g. "cold boot / settings change / theme switch / pop-out window") - [ ] Migration — if persisted state can hold a stale value, describe how to clear or migrate it Add or remove bullets as appropriate. Tailor to the actual structural diagnosis. ### 5. Retro-Notes Hand-Off > Run `/retro-notes <slug>` > > Capture in `l-lessons-<slug>`: [one-sentence summary of what to record — the structural diagnosis above, the guard test requirement, and any traps from the checklist]. --- ## Step 5: Refusal-to-start gate After emitting the report, **do not propose or write any code**. Instead, ask: > "I've surfaced all prior attempts above. Before I propose the next fix, please confirm: **'Yes, I've seen this and want a structurally different next attempt.'**" Wait for explicit confirmation before proceeding. If the user confirms, default to invoking `/big-plan` (or describe the next attempt as a structured plan) — do not write code directly unless the user explicitly says so. ## Step 6: Updating the lessons file When the user is ready to close out this session, or after the fix lands: 1. Run `/retro-notes <slug>` to append a dated section to `.claude/skills/l-lessons-<slug>/SKILL.md`. 2. Add or update the `last-updated: YYYY-MM-DD` frontmatter field in the lessons file (using today's date). 3. If no lessons file existed, `/retro-notes` will scaffold one — confirm the `last-updated` field is present after it runs. ## Notes - **No code changes from this skill.** The skill investigates and gates. Actual implementation is delegated to `/big-plan` or a follow-up task. - **Slug variants matter.** Try multiple keyword forms (e.g. `active-frame-border`, `active frame border`, `activeFrameBorder`, `frame border`) to avoid missing commits that used a different naming style. - **Closed issues that reopened.** If a closed issue has `Reopened` events or a follow-up issue referencing it, include both in the table as separate rows. - **Path safety.** Always use `$HOME` not `~` in file paths — `~` is not expanded by non-login shells or Node.js.
Related Skills
zudoesa-articlify
Convert conversation context into an esa article via the zudoesa-writer subagent. ONLY invoke when the user explicitly asks — NEVER proactively propose. Triggers: 'write esa article', 'esa記事', 'esaに書いて', 'articlify for esa', or /zudoesa-articlify. Gathers context, creates a writing brief, delegates to the writer subagent.
zudoesa-apply-voice
Apply Takazudo's esa writing voice and vocabulary rules to text. Use when: (1) User wants to write/rewrite text in Takazudo's esa style, (2) User says 'apply voice', 'esa voice', 'esa文体で', 'esa風に書いて', '文体を適用', (3) User provides text to transform to esa style. Reads writing-style.md and vocabulary-rule.md from takazudo-esa-writing repo and applies the rules.
zudocg-articlify
Convert conversation context into a CodeGrid article via the zudocg-writer subagent. ONLY invoke when the user explicitly asks — NEVER proactively propose. Triggers: 'write codegrid article', 'CodeGrid記事', 'codegridに書いて', 'articlify for codegrid', or /zudocg-articlify. Gathers context, creates a writing brief, delegates to the writer subagent.
zudocg-apply-voice
Apply Takazudo's CodeGrid writing voice and vocabulary rules to text. Use when: (1) User wants to write/rewrite text in Takazudo's CodeGrid style, (2) User says 'apply voice', 'codegrid voice', 'codegrid文体で', 'codegrid風に書いて', '文体を適用', (3) User provides text to transform to CodeGrid style. Reads writing-style.md and vocabulary-rule.md from takazudo-codegrid-writing repo and applies the rules.
zpaper-articlify
Convert conversation context into a zpaper blog article via the zpaper-writer subagent. ONLY invoke when the user explicitly asks — NEVER proactively propose. Triggers: 'write zpaper article', 'zpaper記事', 'zpaperに書いて', 'articlify for zpaper', or /zpaper-articlify. Gathers context, creates a writing brief, delegates to the writer subagent.
zpaper-apply-voice
Apply Takazudo's zpaper blog writing voice and vocabulary rules to text. Use when: (1) User wants to write/rewrite text in Takazudo's zpaper style, (2) User says 'apply voice', 'zpaper voice', 'zpaper文体で', 'zpaper風に書いて', 'ブログ文体を適用', (3) User provides text to transform to zpaper style. Reads writing-style.md and vocabulary-rule.md from the zpaper repo and applies the rules.
xlsx
Spreadsheet creation, editing, and analysis. Use when working with .xlsx, .xlsm, .csv, .tsv files for: (1) Creating spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modifying existing spreadsheets while preserving formulas, (4) Data analysis and visualization, (5) Recalculating formulas.
x
Facade for development workflows. Routes on two axes: plan-first vs implement-now (escalates to /big-plan -a when the request needs research / decomposition / has unclear scope — the appended -a makes the plan chain into implementation in-session), then single vs multi on the ready-to-build fast paths (/x-as-pr single-topic, /x-wt-teams multi-topic parallel). Use when: (1) User says '/x' followed by dev instructions, (2) User wants to start development without choosing the workflow skill, (3) User says 'dev', 'implement', or 'build' with a task. Default option: -v (verify-ui). Review-loop (-l) is opt-in — without -l the downstream skill runs a single /deep-review pass. Forwards -a (autonomy/auto-chain) and -m (merge at the end + cleanup + CI watch) through every route; auto-fix of raised findings (-f) and issue-raising (-ri) are downstream defaults, with -nf/--no-fix and -nori/--no-raise-issues as the forwarded opt-outs. -a and -m are orthogonal — full hands-off end-to-end is -a -m.
x-wt-teams
Parallel multi-topic development using git worktrees, base branches, and Claude Code agent teams. Use when: (1) User wants to work on multiple related features in parallel, (2) User mentions 'worktree', 'base branch', 'parallel development', 'split into topics', or 'multi-topic'. FULLY AUTONOMOUS — creates worktrees, spawns teams, coordinates everything. Also supports Super-Epic child mode for [Epic] issues from /big-plan with '**Super-epic:** #N' markers (targets the super-epic base branch instead of main).
x-as-pr
Start a development workflow as a draft PR. Creates a NEW branch from the current branch, empty start commit, draft PR targeting the current branch, then implements. ALWAYS creates a new branch by default — produces a nested PR-on-PR when the current branch already has one. Use when: (1) User says 'dev as pr', (2) User wants a PR-first workflow before coding, (3) User passes -s/--stay to reuse the current branch instead of nesting, (4) User passes a GitHub issue URL to implement, (5) User passes --make-issue/--issue to create an issue first. Logs progress via issue comments when an issue is linked.
watch-ci
Watch GitHub PR CI checks in the background and notify on completion. Use when: (1) User wants to monitor CI/CD status, (2) User says 'watch CI', 'check CI', 'monitor checks', or 'wait for CI', (3) User wants to know when checks pass or fail. Runs a background gh polling shell loop (NOT a subagent — near-zero token cost), sends macOS notification on completion. Also handles merged PRs by watching the target branch CI.
w-update-wording-rule
Add or update wording rules (表記ルール) in the w repo's vocabulary-rule.md files. Use when: (1) User says 'add wording rule', 'update wording rule', '表記ルール追加', (2) User wants to add a kanji/hiragana usage rule, (3) User provides a rule like 'X should be Y' with examples.