agentleFS
jakubtobiaszjakubtobiasz/second-brain-template/.agents/skills/project/SKILL.md

project

Skill0 starsChanged 8 days agoMITView on GitHub

Start, update, or close a project in the second brain (30-projects/<name>/ with brief.md and an append-only log.md). Use when the owner says "start a project", "new project", "update project X", "log what we did on X", "where are we on X", "pick up project X", or "close/archive project X".

40 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use next, learn and 7 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.
  • VercelSkill

    next

    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

  • genomewalkerSkill

    learn

    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

  • Microsoft AzureSkill

    test

    Also in 6 projects that use this

  • OpenAISkill

    audit

    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

  • GoogleSkill

    teach

    Teach the user a new skill or concept, within this workspace.

    Also in 4 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 1 is distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 1

    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
  1. Very specific:

    Write brief.md and log.md (from project-log.md, first entry start).

    line 19
  2. Very specific:

    Add to index.md under Projects: - [[30-projects/<name>/brief|<Name>]]: one-line outcome (active).

    line 20
  3. Very specific:

    Read brief.md and the tail of the project's log.md.

    line 24
  4. Distinctive:

    If scope/outcome changed, propose a brief edit.

    line 34
  5. Very specific:

    After start, update, or close, run scripts/qmd-sync.sh.

    line 40
  6. Very specific:

    Read brief.md + the last ~5 log entries + linked artefacts, then answer: goal, current state, last decision, open questions, suggested next …

    line 43
  7. Very specific:

    Update index.md (status archived) and root log.md: ## [YYYY-MM-DD] project | close <name>.

    line 50

“Common” is measured: kept by at least 6 in 10 of the 33 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Project: start · update · resume · close

A project folder lets any agent join cold. brief.md = what it was supposed to be (intent, owner approves changes). log.md = what it became (append-only). Detect the mode from the request; ask if unclear.

Start

  1. Name: kebab-case folder 30-projects/<name>/. Check index.md that it doesn't exist already.
  2. Interview the owner one section at a time, following 90-system/templates/project-brief.md: Why · Outcome · Who it's for · Scope in/out · Constraints & rules · Open questions.
    • Push back once per section on vague answers: "everyone" is not a segment, "more engagement" is not an outcome, "ASAP" is not a deadline. Offer a sharper rewording.
    • "I don't know" is valid → record it under Open questions as - [ ].
    • Pull relevant context from the wiki and link it under Key links.
  3. Write brief.md and log.md (from project-log.md, first entry start).
  4. Add to index.md under Projects: - [[30-projects/<name>/brief|<Name>]]: one-line outcome (active).
  5. log.md (root): ## [YYYY-MM-DD] project | start <name>.

Update (after meaningful work)

  1. Read brief.md and the tail of the project's log.md.
  2. Append to the project log:
    ## [YYYY-MM-DD] <short label>
    - What happened:
    - Decisions: (with why)
    - Artefacts: [[…]] (files saved in the project folder)
    - Next:
  3. Save produced artefacts in the project folder (drafts, specs, analyses).
  4. If scope/outcome changed, propose a brief edit; apply only on the owner's OK.
  5. Knowledge that outlives the project (lessons, facts about people/tools) → file into 20-wiki/ with citations (the project log counts as a source; link it).
  6. Refresh the project's line in index.md (status, one-line state). Root log.md: ## [YYYY-MM-DD] project | update <name>.

The log and index entry decay first because they feel invisible. Don't skip them. After start, update, or close, run scripts/qmd-sync.sh.

Resume ("where are we on X?")

Read brief.md + the last ~5 log entries + linked artefacts, then answer: goal, current state, last decision, open questions, suggested next step. Read-only unless the owner asks for changes.

Close

  1. Set status: archived in brief.md.
  2. Append a final retrospective entry: outcome vs. intent, what worked, what didn't, lessons.
  3. File lessons into the wiki (concept pages or a synthesis) with links back to the project.
  4. Update index.md (status archived) and root log.md: ## [YYYY-MM-DD] project | close <name>.

Hard constraints

  • Project log.md is append-only. Never rewrite past entries; correct with a new entry.
  • brief.md changes need the owner's approval.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.