feature
Skill4 starsChanged 5 days agoMITView on GitHub
Implement an approved plan task by task, with tests and commits. Invoke after a plan is approved, passing the plan document's path.
75 other projects use a version of this.
Adopted by
Most recently taken up by
- mahirhacks/mstacktheir own version, first seen Nov 16, 2026
- arxdsilva/ai-loopstheir own version, first seen Nov 16, 2026
- JeffKarling/Anviltheir own version, first seen Nov 15, 2026
- 5uck1ess/devkittheir own version, first seen Nov 15, 2026
- crbnos/carbontheir own version, first seen Nov 15, 2026
- SatanshuMishra/interphasetheir own version, first seen Nov 15, 2026
Used with
Projects with it also use bug, adopt and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
paulocsbSkillbug
Investigation playbook for fixing a bug. Walks through 5 phases: reproduce → isolate → root cause → propose fix → validate. Forces concrete reasoning with code reads, log inspection, and git blame instead of pattern-matching guesses. Use for any non-trivial defect.
Also in 8 projects that use this
codebycoreySkilladopt
Adopt an existing plan from conversation context into delta-spec format. Use when importing a plan, adopting planning that already happened, capturing plan mode output, or bringing in prior design work.
Also in 4 projects that use this
Google CloudSkillfix
Plan a remediation strategy after a test failure.
Also in 10 projects that use this
marylinSkillrecover
Recover work from a crashed or interrupted session. Use when Claude crashed mid-task, after an unexpected exit, when you see 'stale sessions detected', or when you lost context and need to figure out what was happening.
Also in 3 projects that use this
aegiswizardSkillcontext
Also in 4 projects that use this
AWSSkillmap
Map verified service capabilities against customer-provided control framework and threat model. Produces mapping-results.json, controls-catalog.md, and framework-mapping.md. Supports pluggable frameworks: CCMv4, NIST 800-53, CIS Benchmarks, ISO 27001, etc. Split into 4 focused sub-skills for better accuracy; this skill orchestrates them.
Also in 4 projects that use this
Other versions75 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 75
- crbnos/carbon★ 2.8ksame name
- aeonfun/aeon★ 793same name
- aaronjmars/aeon★ 789same name
- astashov/liftosaur★ 775same name
- me2resh/apexyard★ 542same name
- yicheng47/runner★ 519same name
- bradtraversy/coding-with-ai-course-resources★ 344same name
- garagon/nanostack★ 206same name
- DeL-TaiseiOzaki/claude-code-orchestra★ 199same name
- vide/matedroid★ 86same name
65 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- benchmarkSkill
- bugfixSkill
- designSkill
- deterministic-pr-gatesSkill
- gatesSkill
- parallel-reviewSkill
- pipeline-reviewSkill
- planSkill
- pr-followupSkill
- releaseSkill
- reviewSkill
- specSkill
- statusSkill
- sync-workflowSkill
- testSkill
- trim-contextSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 2 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 69 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Before starting any task:
- Very specific: line 17
Read AGENTS.md/CLAUDE.md — build commands, architecture rules
- Distinctive: line 18
Read the plan document in full
- Very specific: line 19
Read .claude/context/invariants.md if it exists — inviolable rules.
- Very specific: line 20
Read .claude/context/rejections.md if it exists — past review violations.
- Very specific: line 26
After implementation passes tests, run the simplify skill on changed files before committing
- Very specific: line 32
Run the full test suite (including UI tests) after every task — do not proceed if tests fail.
- Very specific: line 33
Never hand-edit project.pbxproj.
“Common” is measured: kept by at least 6 in 10 of the 69 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Feature Agent
You are the Feature Agent for an iOS app project. Your job is to implement an approved plan, task by task, with tests and commits.
Trigger
Invoked after the user approves a plan. The plan path is passed as the argument (e.g. /feature docs/superpowers/plans/2026-05-07-recurring-transactions.md).
Process
Before starting any task:
- Read
AGENTS.md/CLAUDE.md— build commands, architecture rules - Read the plan document in full
- Read
.claude/context/invariants.mdif it exists — inviolable rules; every implementation decision must respect these (skip if absent) - Read
.claude/context/rejections.mdif it exists — past review violations; do not repeat these patterns (skip if absent) - Confirm you are on a
feature/<name>branch (create it offdevelopif not)
Per-task rules
- Iron law before the RED step of each task: no production code without a failing test that already exists. Write the test, run it, and confirm it fails for the expected reason (feature missing, not a typo or setup error) before writing a single line of implementation. If you catch yourself writing production code first "to see the shape of it" or "just this once," that's the rationalization to stop on — delete what you wrote and start over from a failing test. A test that only exists after the code it verifies proves nothing: it can't fail on the behavior it's supposedly protecting, so passing on the first run is not evidence, it's an artifact of writing the test to match code that already exists. (A plugin's
enabledPluginsflag beingtruein.claude/settings.jsondoes not guarantee its skills are actually invocable in a given environment — confirmed the hard way in the parent project. Don't gate this discipline on an external skill invocation; keep it self-contained.) - If the task adds or modifies a mutation on a shared/persisted entity (create, update, or delete on a persisted type, e.g. an
@Modelclass under swiftdata), the failing test written first must cover both a repeat-call/duplicate case (e.g. calling the same mutation twice with the same identity) and a missing-required-field case — not just the happy path. TDD's write-test-first sequencing alone does not force imagining a failure mode, only that some test exists for whatever was imagined — this rule closes the specific gap where a missing-guard bug ships because the negative case was never considered. If your project keeps a bug postmortem or decision log, cite the specific past incident here once you have one. - After implementation passes tests, run the
simplifyskill on changed files before committing - If this task's implementation introduces a new protocol declaration, or adds/modifies a mutation on a persisted type (the same shapes
/gatesGate 8 and Gate 10 check for), run a doubt-driven review before the GREEN commit: hand a fresh-context subagent only the diff plus this task's acceptance criteria from the plan — not your reasoning or this session's conversation — and instruct it explicitly to find problems with the change or state plainly that it found none. Address real findings, or record why not; bounded to 2 rounds of this cycle. Log any real finding to.claude/context/incidents.md(create the file with a one-line header if it doesn't exist, matching/bugfix's existing convention) so/reviewand future/bugfixruns flag a repeat as high severity. This exists because/review's isolated reviewer only sees the change once the PR is open (seereview/SKILL.md's "Context isolation" section), and/parallel-review, the other pre-PR review, is optional and run manually (it is not in the standard pipeline in AGENTS.md/CLAUDE.md) — so nothing else in the standard pipeline catches a bad call in isolation while it's still cheap to reverse. - Append a one-line entry to the
## [Unreleased]section ofCHANGELOG.md(create the section if absent) - Two commits per task, in this order — not one:
- RED commit — the new/modified test file(s) only, no production code. Commit message should quote the actual failing-test output (the assertion/error line, not just "test written"). Never bundle a test file and the production file it exercises in the same commit — a single commit for both makes the red step unverifiable from git history (see
/gatesGate 9). - GREEN commit — the production code that makes it pass, plus the
simplifypass andCHANGELOG.mdentry. Commit message should quote the passing-test output line.
- RED commit — the new/modified test file(s) only, no production code. Commit message should quote the actual failing-test output (the assertion/error line, not just "test written"). Never bundle a test file and the production file it exercises in the same commit — a single commit for both makes the red step unverifiable from git history (see
- Run the full test suite (including UI tests) after every task — do not proceed if tests fail. Use the "Full test suite" command in AGENTS.md/CLAUDE.md; never add
-skip-testingor-only-testingflags. - Never hand-edit
project.pbxproj. With synchronized groups (scripts/detect_file_registration.sh . <AppName>printssynchronized) files auto-compile; withclassicgroups runruby scripts/register_files.rb . <AppName> <new files>after creating each file; onxcprojorstop, ask the human
Build commands (all run from git root — see AGENTS.md/CLAUDE.md for exact path)
# Full test suite
xcodebuild test <BuildTarget> -scheme <AppName> \
-destination 'platform=iOS Simulator,name=<simulator from AGENTS.md/CLAUDE.md>' \
2>&1 | grep -E "Test.*passed|Test.*failed|TEST SUCCEEDED|TEST FAILED"
# Single suite
xcodebuild test <BuildTarget> -scheme <AppName> \
-destination 'platform=iOS Simulator,name=<simulator from AGENTS.md/CLAUDE.md>' \
-only-testing:<AppName>Tests/<SuiteName> \
2>&1 | grep -E "Test.*passed|Test.*failed|BUILD"Project settings
Read project in scripts/pipeline_lanes.json: persistence (swiftdata | coredata | realm | none), ui (swiftui | uikit), architecture (mvvm | mvc | viper). If the key is absent, assume swiftdata, swiftui, mvvm. Apply the persistence and UI rules below for the configured values, not SwiftData and SwiftUI by default. Read "ViewModel" as Controller (mvc) or Presenter (viper).
Architecture rules (from AGENTS.md/CLAUDE.md)
- Domain Services: zero persistence-framework imports (SwiftData, CoreData, RealmSwift)
- Repository Protocols: Foundation-only imports
- <type-safety rule from AGENTS.md, e.g. money values:
Decimal, neverDouble> - ViewModels (or Controllers / Presenters) depend on protocols, never concrete implementations
- Views contain no business logic
Done when
All tasks complete, full test suite green, /test's coverage-gap audit done, and all blocking /gates criteria pass (Gate 8 is advisory). Then open a PR to develop and run /pr-followup, which runs code-review (medium, app lane only) and then /review and records each in the PR body for the review-evidence check.
To drive the entire feature-to-gates cycle autonomously:
/loop run /feature on the next uncovered task from the plan. Then run /gates. Stop when all blocking gates pass.Or target only gate-fixing after tasks are done:
/loop Fix failing gates. Stop when all blocking gates pass (Gate 8 abstraction bloat is advisory, never blocks): tree clean and SHA recorded, build succeeds, all tests pass with a non-zero executed count, no TODO/FIXME/HACK, branch name valid, CHANGELOG updated, coverage ≥80% on new files, security review clean, RED commit precedes GREEN commit for every new file in a scoped layer, architecture & layer-rule compliance clean, gate integrity clean.Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

