project
Skill19 starsChanged 22 days agoApache-2.0View on GitHub
Development planning tool for tracking project progress, organizing Issues, and syncing the roadmap
39 other projects use a version of this.
Adopted by
Most recently taken up by
- jakubtobiasz/second-brain-templatetheir own version, first seen Nov 15, 2026
- br3eze-code/br3eze-codetheir own version, first seen Nov 11, 2026
- HurricaHjz/second-yourselftheir own version, first seen Nov 9, 2026
- saksham10arora-dotcom/everything-claude-codextheir own version, first seen Nov 1, 2026
- kriscard/Skillstheir own version, first seen Oct 28, 2026
- jantichy/claudetheir own version, first seen Oct 27, 2026
Used with
Projects with it also use ingest, next and 8 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.
JaimeGBASkillingest
Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base
Also in 5 projects that use this
VercelSkillnext
Next.js renderer for json-render that turns JSON specs into full Next.js applications with routes, layouts, SSR, and metadata. Use when working with @json-render/next, building Next.js apps from JSON specs, or creating AI-generated multi-page applications.
Also in 3 projects that use this
Microsoft AzureSkilllint
Run all linting and spell checking for TypeScript and Rust code. Run this before committing to catch style issues, clippy warnings, and misspellings.
Also in 4 projects that use this
genomewalkerSkilllearn
Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.
Also in 8 projects that use this
OpenAISkillaudit
Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.
Also in 5 projects that use this
GoogleSkillteach
Teach the user a new skill or concept, within this workspace.
Also in 4 projects that use this
Other versions39 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 39
- fleetdm/fleet★ 7.2ksame name
- samchon/typia★ 6ksame name
- samchon/nestia★ 2.2ksame name
- cwinvestments/memstack★ 433same name
- AlpacaLabsLLC/skills-for-architects★ 420same name
- Achuan-2/siyuan-plugin-task-note-management★ 227same name
- HurricaHjz/second-yourself★ 150same name
- HurricaHjz/SecondSelf★ 150same name
- Soul-Brews-Studio/arra-oracle-skills-cli★ 121same name
- saksham10arora-dotcom/everything-claude-codex★ 96same name
29 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 repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- autopilotSkill
- buildSkill
- code-reviewSkill
- implement-pluginSkill
- implementSkill
- license-checkSkill
- orchestrateSkill
- pentest-proxySkill
- prSkill
- review-gateSkill
- security-reviewSkill
- testSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 11 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 32 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 87
After approval, execute create_issue / update_issue
- Distinctive: line 125
If a new feature requires adding a field to the config struct, explicitly include a config support Issue
- Distinctive: line 131
Always get user approval before creating Issues
- Distinctive: line 132
Do not create Issues not in the roadmap
- Distinctive: line 133
When overwriting an existing Issue's description, show the diff explicitly
- Distinctive: line 138
When the roadmap has only a milestone description (no per-Issue table) — typical for newly-added milestones — run the milestone-planner …
- Very specific: line 143
Read .claude/agents/milestone-planner.md and .claude/agents/design-reviewer.md (the planner injects design-reviewer as a sub-step).
- Very specific: line 168
After approval, create each Issue via mcp__linear-server__save_issue with priority, scope, dependencies (blockedBy), and acceptance …
- Distinctive: line 174
Update roadmap documents to match the actual state after implementation is complete.
- Distinctive: line 183
Update each milestone section in the roadmap:
- Distinctive: line 184
Update status markers in Issue tables (✅ Complete, 🔄 In Progress, ⏳ Not Started)
- Distinctive: line 185
Update milestone progress summary
- Very specific: line 188
After approval, apply with mcp__linear-server__update_document
- Distinctive: line 214
Always get user approval before updating the document
- Distinctive: line 215
Do not change the roadmap structure (milestone order, descriptions) — only update statuses
“Common” is measured: kept by at least 6 in 10 of the 32 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
/project
A skill that handles the planning and tracking sides of the "plan → implement → track" development cycle. Provides milestone progress overview, Issue creation from the roadmap, and post-implementation document sync.
Fixed Parameters
- Team: Usk6666
- Project: yorishiro-proxy
- Roadmap doc ID: d413edd7-d296-433a-ab94-11d4dd57d883
Subcommands
/project status— Overview of milestone progress/project plan <milestone>— Gap analysis between roadmap and Linear Issues, with Issue creation. If the roadmap has no Issue table for the target milestone (greenfield), run the milestone-planner agent to derive Issues from the milestone description + spec — see "Greenfield Mode" below./project sync— Update roadmap documents after implementation is complete
/project status
The entry point for checking milestone progress and deciding what to work on next.
Steps
- Fetch all milestone progress with
mcp__linear-server__list_milestones(project=yorishiro-proxy) - Fetch the following in parallel:
mcp__linear-server__list_issues(team=Usk6666, project=yorishiro-proxy, state=started)mcp__linear-server__list_issues(team=Usk6666, project=yorishiro-proxy, state=backlog)mcp__linear-server__list_issues(team=Usk6666, project=yorishiro-proxy, state=unstarted)
- Group Issues by
projectMilestonefield - Report the following:
Output Format
## Project Progress
### Milestone Progress
| Milestone | Progress | Remaining Issues | Status |
|-----------|----------|-----------------|--------|
| M1: Foundation | 100% | — | Complete |
| M2: MCP Interface v2 | 79% | 3 issues | ← ACTIVE |
| M3: Active Testing | 0% | N issues | Not started |
| M4: Multi-Protocol | 0% | N issues | Not started |
| M5: Production Ready | 0% | N issues | Not started |
### Active: M2 — MCP Interface v2
| ID | Title | Status | Priority |
|----|-------|--------|----------|
| USK-79 | ... | Backlog | High |
| USK-80 | ... | Todo | Normal |
| ...
### Blockers
- M3 depends on M2 completion (currently 79%)
### Recommended Actions
- `/orchestrate milestone M2` to implement remaining 3 Issues
- Or `/project plan M3` to prepare M3 Issues in advance/project plan <milestone>
The most important subcommand for setting up prerequisites for orchestrate. Closes the gap between the roadmap (desired state) and Linear (actual Issues).
Steps
- Fetch roadmap document with
mcp__linear-server__get_document(id=d413edd7-d296-433a-ab94-11d4dd57d883) - Parse the Issue table in the target milestone section
- Extract Issue ID, title, description, priority, and dependencies
- Fetch existing Issues for that milestone with
mcp__linear-server__list_issues(team=Usk6666, project=yorishiro-proxy)- Filter by milestone (fetch all then filter if milestone parameter filtering is unavailable)
- Gap analysis:
- In roadmap but not in Linear → Propose Issue creation
- In Linear but milestone unassigned → Propose assignment fix
- Issues with insufficient description → Propose description improvement
- Present analysis results to user and get approval
- After approval, execute
create_issue/update_issue - Also set dependency relationships (
blockedBy/blocks) between created Issues
Output Format
## <Milestone Name> — Issue Plan
### To Create
| # | Title | Priority | Basis |
|---|-------|----------|-------|
| 1 | Intercept rule engine | High | Roadmap M3 section |
| 2 | Intruder engine | High | Roadmap M3 section |
| ...
### Existing (No changes)
| ID | Title | Milestone | Status |
|----|-------|-----------|--------|
| USK-64 | Auto-transform rules | M3 | Backlog |
### Proposed Modifications
| ID | Change |
|----|--------|
| USK-XX | Milestone unassigned → assign to M3 |
| USK-YY | Improve description (reflect roadmap spec) |
### Dependencies
| Issue | blockedBy |
|-------|-----------|
| #2 Intruder engine | #1 Intercept rule engine |
Create N Issues and update M? Proceed?Config Checklist
At the final stage of Issue splitting, confirm the following (see "Config Checklist for New Feature Milestones" in CLAUDE.md):
- If a new feature requires adding a field to the config struct, explicitly include a config support Issue
- Same applies if config validation or init function changes are needed
- Include a config → runtime path integration test Issue if needed
Notes
- Always get user approval before creating Issues
- Do not create Issues not in the roadmap
- When overwriting an existing Issue's description, show the diff explicitly
- Infer dependency relationships from Issue content and set blockedBy/blocks
Greenfield Mode (no roadmap Issue table)
When the roadmap has only a milestone description (no per-Issue table) — typical for newly-added milestones — run the milestone-planner agent to derive a structured Issue breakdown from the milestone description, completed-milestone public surface, and applicable specs.
Steps
- Confirm with the user that greenfield-mode planning is wanted (otherwise the roadmap is the source of truth and Step 2-7 above apply as-is).
- Read
.claude/agents/milestone-planner.mdand.claude/agents/design-reviewer.md(the planner injects design-reviewer as a sub-step). - Replace the planner's placeholders:
| Placeholder | Value |
{{MILESTONE_NAME}} | Target milestone name (e.g., "M5") |
{{MILESTONE_DESCRIPTION}} | Full description from mcp__linear-server__get_milestone |
{{SPEC_REFERENCES}} | Paths to spec/design docs that apply (e.g., docs/rfc/envelope.md, protocol RFCs) |
{{COMPLETED_CONTEXT}} | One-paragraph summary of public surface from completed milestones the new work will integrate with |
{{PRODUCT_IDENTITY}} | Read from .claude/skills/review-gate/SKILL.md Phase 1-4 "Product context" block — single source of truth |
{{PRINCIPLES}} | The MITM Implementation Principles from CLAUDE.md (the 6-item list). Quote verbatim. |
{{DESIGN_REVIEW_AGENT}} | Full Prompt Body section from .claude/agents/design-reviewer.md (the planner runs design review at milestone scope as Step 2 of its process) |
{{CHECKLISTS}} | Whichever of "Config Checklist for New Feature Milestones" / "e2e Test Checklist for New Protocol Addition" (both from CLAUDE.md) apply. Quote verbatim — the planner enforces them as mandatory checks. |
- Launch:
Agent(
description="Plan milestone <name>",
subagent_type="general-purpose",
prompt=<composed prompt>
)- Present the planner's output — Issue breakdown, dependency graph, resolved decisions, unresolved decisions for user input, recommended order — and get user approval.
- After approval, create each Issue via
mcp__linear-server__save_issuewith priority, scope, dependencies (blockedBy), and acceptance criteria. Then update the roadmap document to embed the new Issue table so subsequent/project planruns hit the regular gap-analysis path instead of greenfield mode.
/project sync
Update roadmap documents to match the actual state after implementation is complete.
Steps
- Fetch roadmap document with
mcp__linear-server__get_document(id=d413edd7-d296-433a-ab94-11d4dd57d883) - Fetch latest progress with
mcp__linear-server__list_milestones(project=yorishiro-proxy) - Fetch the following in parallel:
mcp__linear-server__list_issues(team=Usk6666, project=yorishiro-proxy, state=completed)mcp__linear-server__list_issues(team=Usk6666, project=yorishiro-proxy, state=started)
- Update each milestone section in the roadmap:
- Update status markers in Issue tables (✅ Complete, 🔄 In Progress, ⏳ Not Started)
- Update milestone progress summary
- Record completion date if available
- Show the diff to the user and get approval
- After approval, apply with
mcp__linear-server__update_document
Output Format
## Roadmap Sync
### Changes
- M2: Progress 79% → 100% (Complete)
- USK-75: ⏳ → ✅
- USK-78: ⏳ → ✅
- USK-79: ⏳ → ✅
### Updated Milestone Summary
| Milestone | Progress | Status |
|-----------|----------|--------|
| M1: Foundation | 100% | Complete |
| M2: MCP Interface v2 | 100% | Complete |
| M3: Active Testing | 0% | Next target |
Update roadmap? Proceed?Notes
- sync fetches completed Issues, but only for the purpose of document updates
- Always get user approval before updating the document
- Do not change the roadmap structure (milestone order, descriptions) — only update statuses
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.

