Not in the top 1,000 by GitHub stars
Are you the author? Verify on GitHub to add your tagline and up to 3 links, queue a re-scan (it usually runs within the hour, once every 24 hours per repository), dispute a security signal and get alerts. Rankings never change.
Claude Code skill that generates structured product knowledge bases from codebase scanning
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
be3a4875d72e → be3a4875d72e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → be3a4875d72e
No earlier version was observed for comparison.
10GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days
Heat
0.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Web upvotesNot available
- Weekly Hot picksNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- codewiki
/
How it works
codewiki
When your agent uses it
Generate a structured product knowledge base from codebase scanning. Creates a codewiki/ folder with architecture docs, user flows, API reference, service maps, and more. Also generates CLAUDE.md. Handles single repos, monorepos, and multi-repo microservices. Use when asked to document a project, generate a knowledge base, map architecture, create onboarding docs, or set up CLAUDE.md for a codebase.
What it loads into context
Frontmatter
108 tokensAlways available to the agent
SKILL.md
6,875 tokensWhen the skill is activated
Reference documents
5,088 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- HARD RULES
- Phase 1: Product Context Gathering (MANDATORY — DO NOT SKIP)
- Context Window Management (Multi-Repo Strategy)
- Phase 2: Codebase Analysis
- Phase 3: User Flow Discovery (Interactive)
- Phase 4: Architecture Checkpoint (BEFORE writing files)
- Phase 5: Knowledge Base Generation
- Phase 6: CLAUDE.md Generation
- Phase 7: Git & Repository Setup
- Behavioral Guidelines
Files
LICENSEasset1,064 bytesREADME.mddoc15,067 bytesSKILL.mdcore28,996 bytesSKILL.mdcore28,996 bytesSKILL.mdcore28,996 bytesSKILL.mdcore28,996 bytesSKILL.mdcore28,996 bytesSKILL.mdcore28,996 bytesSKILL.mdcore28,996 bytesSKILL.mdcore28,996 bytesSKILL.mdcore28,996 bytesSKILL.mdcore28,996 bytesSKILL.mdcore28,996 bytesSKILL.mdcore28,996 bytesSKILL.mdcore28,996 bytesSKILL.mdcore28,996 bytestemplates/architecture.mddoc998 bytestemplates/claude-md.mddoc1,158 bytestemplates/events.mddoc1,117 bytestemplates/readme.mddoc1,845 bytestemplates/service-map.mddoc1,462 bytestemplates/user-flow.mddoc920 bytes
Read SKILL.md
# CodeWiki — Product Knowledge Base Generator
Scan code, fetch product context, discover user flows, and generate a structured `codewiki/` knowledge base.
Output templates are in this skill's `templates/` directory. Read each template only when generating that specific file — do NOT load all templates at once.
## HARD RULES
1. **Phase 1 is not optional.** Product context is the difference between a useful wiki and a mechanical code listing. Complete it before scanning. If user can't answer, use the code-first fallback.
2. **Multi-repo workspace must be verified before scanning.** If repos aren't in a shared parent folder, stop and help the user set it up.
3. **Never scan all repos simultaneously.** Use Scan → Write to `_scratch/` → Carry 30-line summary → Next. This is how you survive large multi-repo projects.
4. **Never skip a service in microservices.** User flows that touch 5 services are useless if one is undocumented. Every service gets at least a lightweight scan.
5. **Scan in priority order.** Infrastructure/contracts → gateway → frontends → core business services → supporting services.
6. **Report progress between repos.** Tell the user what you found and which repo is next. Do not ask for permission between repos — just continue. Only pause on errors or contradictions.Skills included
- codewiki
Repository facts
- License
- MIT
- Created
- Mar 6, 2026
- Last pushed
- Mar 6, 2026
- Forks
- 0
- Open issues
- 0
- Project activity
- Slowing
Before you install
Network or broad shell checked with an earlier scanner versionAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 13 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No executable scripts found
- 10 network referencesin 2 files: SKILL.md:649 README.md:22
- 2 possibly dangerous shell commandsin 1 file: SKILL.md:549
- 1 possible reference to secretsin 1 file: SKILL.md:346
- No broad tool permissions found
- No hidden or obfuscated text found
- No instruction overrides found
- No Hot vote requests found
Show all 13 signals by file
README.md
SKILL.md
- Possible access to secretsline 346
[Credential-related source omitted] - Possibly dangerous shell commandline 549
[Credential-related source omitted] - Possibly dangerous shell commandline 581
[Credential-related source omitted] - Possible network accessline 649
[Credential-related source omitted] - Possible network accessline 650
[Credential-related source omitted] - Possible network accessline 651
[Credential-related source omitted] - Possible network accessline 670
[Credential-related source omitted] - Possible network accessline 671
[Credential-related source omitted] - Possible network accessline 672
[Credential-related source omitted]
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code may do, not why.
Signal confidence: 13 facts
- Possible network access in prose of documentationREADME.md:22Low confidence
- Possible network access in code of documentationREADME.md:85Low confidence
- Possible network access in prose of documentationREADME.md:113Low confidence
- Possible network access in prose of documentationREADME.md:206Low confidence
- Possible access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valueSKILL.md:346Low confidence
- Possibly dangerous shell command in code of the SKILL.mdSKILL.md:549High confidence
- Possibly dangerous shell command in code of the SKILL.mdSKILL.md:581High confidence
- Possible network access in prose of the SKILL.mdSKILL.md:649Low confidence
- Possible network access in prose of the SKILL.mdSKILL.md:650Low confidence
- Possible network access in prose of the SKILL.mdSKILL.md:651Low confidence
- Possible network access in prose of the SKILL.mdSKILL.md:670Low confidence
- Possible network access in prose of the SKILL.mdSKILL.md:671Low confidence
- Possible network access in prose of the SKILL.mdSKILL.md:672Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Frontmatter field user-invocable in SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
