Borrowing it
Nothing to install: this file belongs to jmrplens/gitlab-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jmrplens/gitlab-mcp-server/main/.github/skills/update-project-documentation/SKILL.mdgit clone --depth 1 https://github.com/jmrplens/gitlab-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jmrplens/gitlab-mcp-server/update-project-documentation)<a href="https://agentmods.dev/skills/jmrplens/gitlab-mcp-server/update-project-documentation"><img src="https://agentmods.dev/badge/skills/jmrplens/gitlab-mcp-server/update-project-documentation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jmrplens/gitlab-mcp-server/update-project-documentation"><img src="https://agentmods.dev/badge/skills/jmrplens/gitlab-mcp-server/update-project-documentation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.02360 |
| Opus 5.5 | $0.00023 | $0.00944 |
| Sonnet 5.5 | $0.00012 | $0.00472 |
| Haiku 4.5 | $0.00006 | $0.00236 |
Grade A, and why
update-project-documentation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Project Documentation
Primary Directive
Update existing documentation to reflect current source code changes. Perform a delta analysis between the implementation and documentation, then surgically update only the affected sections while preserving the overall document structure, style, and formatting.
The documentation lives in two places, one per audience (ADR-0025):
- User documentation is the site only:
site/src/content/docs/in English and its Spanish twin undersite/src/content/docs/es/, published athttps://docs.jmrp.io/gitlab-mcp-server/. An English page and its twin change together. Follow theupdate-starlight-docsskill for the page map, the generated pages and the site's checks. - Contributor documentation is
docs/development/, plusCLAUDE.md,AGENTS.mdand.github/for the guidance AI assistants read. Besidedocs/development/,docs/holds only a README that points at the site.
Execution Context
This skill is triggered after code changes to ensure documentation stays in sync. It focuses on efficiency — only updating what has changed rather than regenerating entire documents.
Analysis Phase
Step 1: Identify Changed Code
- Check recent changes using git diff or by examining the files provided
- If no specific files are indicated, scan all Go source files for modifications
- Build a list of changed exported types, functions, constants, and configurations
- Identify new, modified, or removed public APIs
Step 2: Map Changes to Documentation
For each code change, identify which documentation files are affected:
Site pages are named by slug: operations/http-server is site/src/content/docs/operations/http-server.mdx and site/src/content/docs/es/operations/http-server.mdx.
| Change Type | Affected Documentation |
|---|---|
| New exported type/function | Its godoc comment (make check-godocs), possibly the tools or resources pages of the site |
| Modified function signature | Godoc comment, tools reference, examples |
| New MCP tool | The site's per-domain tool reference, which is generated: run make gen-tool-reference (a new catalog group first needs its entry in cmd/gen_tool_reference/domains.json), make gen-site-stats for the counts the site prints and make gen-action-grants for the fine-grained table, which holds one row per action |
| New MCP resource or prompt | Site page tools/resources-prompts; docs/development/architecture.md (Resources and prompts: where each lives) |
| Configuration change | Site pages configuration, reference/environment and reference/cli, the variable and flag lists in docs/development/configuration.md and the summary table in CLAUDE.md, and the environment variable and flag tables in .github/copilot-instructions.md |
| New package | The Project Structure of docs/development/development.md, the packages tables of docs/development/architecture.md and the project tree, one line per entry in CLAUDE.md and annotated in docs/development/repository-map.md; docs/development/cmd-utilities.md for a new cmd/ utility |
| Architecture change | Site page architecture for what a user sees (transports, surfaces, security model), diagrams included; docs/development/architecture.md (packages, the path a call takes, handler patterns), docs/development/development.md and docs/development/tool-surfaces-and-action-core.md for how the code is put together |
| Error handling change | Site pages operations/error-handling and operations/troubleshooting; docs/development/error-handling.md for the classification and wrapping functions |
| Capability change | Site pages under capabilities/; docs/development/capabilities.md for the progress, elicitation and completion APIs and the icons |
| Build/deploy change | docs/development/development.md, and docs/development/distribution.md for the bundles and the channel publishers; site pages under install/ and operations/remote-deployment |
| Removed API | All referencing documents |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed 06d860b5d3c7
- yesterday Changed 0aae4a68c32e
- 6d ago Changed 24fb50321f36
- 7d ago Changed cac9d60e0c3e
- 16d ago Changed · +11 lines · +18 tokens per session 92e6b49f7318
- 1mo ago Changed · +1 lines c42550fecc77
- 1mo ago First seen · 150 lines · 40 tokens per session scan A f95fd1aa0e74
update-project-documentation is a skill published in the GitHub repository jmrplens/gitlab-mcp-server (46 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 2,360 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
snip
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
goai
GoAI is a Go SDK for AI applications. One unified API across 25+ LLM providers. Inspired by the Vercel AI SDK, adapted to Go idioms (generics, interfaces, channels).
golang-benchmark
Run reproducible Go benchmarks, profiling, benchstat and CI regression analysis.
implement-rfc
Implement one RFC: check its predecessors, present a plan for approval, write the code, then demonstrate every acceptance criterion.