agentleFS
tethertotetherto/qvac/.agents/skills/qv-dev-diary-setup/SKILL.md

qv-dev-diary-setup

Skill697 starsChanged 18 days agoApache-2.0View on GitHub

Set up the opt-in local dev diary for any developer. Use when the user asks to enable diary logging, initialize diary capture, run diary --init, or configure local daily work updates.

  • Reads credentials

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 7 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill only for setup/enable/disable.

    line 11
  2. Very specific:

    When using --asana or an Asana config file, first show these instructions to the user before checking whether ASANA_ACCESS_TOKEN exists:

    line 15
  3. Distinctive:

    Create a Personal Access Token.

    line 18
  4. Distinctive:

    No OAuth app and no Asana MCP server are needed.

    line 21
  5. Very specific:

    Do not run a raw shell check like test -n "$ASANA_ACCESS_TOKEN" or echo "$ASANA_ACCESS_TOKEN".

    line 68
  6. Very specific:

    Run the init command directly and let diary-cli.mjs resolve the token from process.env or the user's default shell startup files:

    line 69
  7. Distinctive:

    If the helper reports a missing token, stop after showing its output.

    line 75
  8. Distinctive:

    If init succeeds, confirm diary status:

    line 76
  9. Distinctive:

    Do not enable diary capture unless init succeeds.

    line 84
  10. Distinctive:

    Do not ask for Slack channel during init.

    line 85
  11. Distinctive:

    Do not write tokens, Asana IDs, or diary entries into repo files.

    line 86
  12. Very specific:

    If Asana is requested, walk the user through creating ASANA_ACCESS_TOKEN and verify /users/me.

    line 87
  13. Very specific:

    If an Asana config path is provided, it must contain only shared workspace/project/section/custom-field metadata.

    line 88
  14. Very specific:

    Never preflight token presence with raw shell env checks.

    line 89

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “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

Dev Diary Setup

Sets up local diary capture. The diary is off by default and only turns on after initialization succeeds.

Use this skill only for setup/enable/disable. For reading, editing, or adding diary entries after setup, use qv-dev-diary.

Asana Token Setup

When using --asana or an Asana config file, first show these instructions to the user before checking whether ASANA_ACCESS_TOKEN exists:

  1. Open Asana developer console.
  2. Create a Personal Access Token.
  3. Description suggestion: Local qvac-pr-skills.
  4. Permission model: Asana Personal Access Tokens do not require choosing scopes in this setup. The token acts as the current Asana user and can access whatever that user can access. For this workflow, that user must be able to read the workspace/project/tasks; for sync actions, the user must also be allowed to comment, move, and complete tasks in that project.
  5. No OAuth app and no Asana MCP server are needed.
  6. Store it in your default shell startup file or export it in the current shell. Coding agents may not inherit the app environment, so the helper falls back to asking your default shell for this variable.
export ASANA_ACCESS_TOKEN='<token>'
  1. Verify manually:
curl https://app.asana.com/api/1.0/users/me \
  -H "Authorization: Bearer $ASANA_ACCESS_TOKEN"

Docs: Asana personal access token

Commands

Basic local diary only:

node .agents/skills/_lib/developer-workflow/diary-cli.mjs --init --basic

Local diary plus Asana config import:

node .agents/skills/_lib/developer-workflow/diary-cli.mjs --init /path/to/asanaconfig.json

Status:

node .agents/skills/_lib/developer-workflow/diary-cli.mjs --status

Disable:

node .agents/skills/_lib/developer-workflow/diary-cli.mjs --off

Workflow

For Asana-backed setup:

  1. Present the Asana Token Setup section above.
  2. Do not run a raw shell check like test -n "$ASANA_ACCESS_TOKEN" or echo "$ASANA_ACCESS_TOKEN". That only checks the agent process environment and bypasses the helper's default-shell fallback.
  3. Run the init command directly and let diary-cli.mjs resolve the token from process.env or the user's default shell startup files:
node .agents/skills/_lib/developer-workflow/diary-cli.mjs --init /path/to/asanaconfig.json
  1. If the helper reports a missing token, stop after showing its output. Do not replace it with a shorter "export token" message.
  2. If init succeeds, confirm diary status:
node .agents/skills/_lib/developer-workflow/diary-cli.mjs --status

Rules

  • Do not enable diary capture unless init succeeds.
  • Do not ask for Slack channel during init.
  • Do not write tokens, Asana IDs, or diary entries into repo files.
  • If Asana is requested, walk the user through creating ASANA_ACCESS_TOKEN and verify /users/me.
  • If an Asana config path is provided, it must contain only shared workspace/project/section/custom-field metadata.
  • Never preflight token presence with raw shell env checks; always use diary-cli.mjs / asana.mjs so default-shell fallback is applied.

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.