records
Use when you need to write down what was decided, what happened, or what a bead needs, so whoever reads it next inherits it.
Skill by zookanalytics
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/zookanalytics-records
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, writing, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/records
What's inside
- Skill name
records- Description
- Use when you need to write down what was decided, what happened, or what a bead needs, so whoever reads it next inherits it. Covers recording an outcome or a finding by appending to a bead's notes, summing up long notes under a Current state heading, and setting the one-line headline the board shows for a bead (its takeaway). To ask a person to decide, use waits; for a durable document such as a spec or an analysis, use filing-documentation.
- License
- MIT
- Compatibility
- Requires Gas City (gc CLI, $GC_* env, beads).
- Instructions
- 59 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Records: what a bead's next reader inherits A bead carries its own record. The next worker, sitting or person who reads it starts from what is written there, not from your context, which ends with your session. Each option says what the record means, who reads it, and the one writer that sends it. The writers are the gc-toolkit pack's own scripts. `gc <binding> scripts-dir` prints their directory in the pack as gc loaded it, so each example calls the pack's copy inside the command itself, and runs in a fresh shell. `<binding>` is the name the city imports the pack under, which gc puts in front of this skill's name: `gc-toolkit` in `gc-toolkit.records`. `gc skill list` prints it in this skill's FROM column. ## Record an outcome on a bead The message is what was decided or found, why, and what changed. The next reader of the bead picks it up: a sitting primes from the bead's notes, and a worker reads them before it starts. Writer: `gc bd update <bead> --append-notes "<decision or finding, the reason, what changed>"`. Notes are append-only. `--notes` replaces the whole field and erases every note other writers left there, so never use it. When the notes have grown past a quick read, append a current-state block: where things stand, the decisions in force, and the open questions. The newest current-state block is the one in force, so a reader starts there: ```bash gc bd update <bead> --append-notes "## Current state ($(date -u +%Y-%m-%d)) <where things stand> Decisions in force: <each decision in force> Open questions: <each open question, or none>" ``` A bead's notes are operational state. A durable document, such as a spec, an analysis or a decision record, is a file in a repo, filed through the filing-documentation skill. A sitting writes no files, so it files a bead for the document instead (the work skill). ## Set the headline the board shows The message is one sentence saying what the bead needs now. The helm board shows it as the bead's NEEDS cell, and `doctor/check-wait-is-an-edge` checks the wait it declares against the bead's `blocks` edges. Writer: `"$(gc <binding> scripts-dir)/gc-helm.sh" takeaway <bead> "<what it needs now, at most 140 characters>" --no-wait` when the bead waits on nothing, or `--waiting-on <bead>` (repeatable) for each bead it waits on. Each named wait is also written as a `blocks` edge, best-effort: an edge that will not take only warns, so read it back when the wait matters (the waits skill). Saying neither parks the bead on prose, which the doctor reports unless a live `blocks` edge holds it. In a sitting, the hold and the sign-off write the headlines (the converse-hold and converse-settle steps). The one other headline a sitting writes is a stand-down, which stops work in flight (the work skill).
From zookanalytics/gc-toolkit, MIT.
More from zookanalytics/gc-toolkit
- 0.620score
review-correctness
zookanalytics
The method for the correctness check, the standing review of whether a change is correct and safe as merged.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
review-arch
zookanalytics
The method for the arch check — the Architect, steward and gatekeeper of the repo's high-level architecture.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
review-triage
zookanalytics
The method for the triage check — a broad, cheap scan that does not judge a change but decides which specialist checks it needs, then records that decision by…
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
learning-distill
zookanalytics
The promotion-judgment rubric for the feedback-learning loop — use when you are the mol-feedback-distiller judging pending feedback observations into…
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
prs
zookanalytics
Use when something has to happen to an open pull request or its anchor bead.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
review-pm
zookanalytics
The method for the PM check — the product lens on a change, reviewed by a peer to the author rather than an order-taker.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
work
zookanalytics
Use when you have to say that something needs doing, carry out a decision about who does it, or change work already asked for.
SkillAFreshness: A★ 5Claude Code +9 - 0.616score
gc-demo-script
zookanalytics
Generates a demo:capture-format script from a closed Gas City work bead by reading the bead tree, git commits, and PR diff
SkillAFreshness: A★ 5Claude Code +9 - 0.615score
waits
zookanalytics
Use when something must not go yet because it has to wait for other work to land, or for a person to decide or act.
SkillAFreshness: A★ 5Claude Code +9 - 0.615score
review-demo
zookanalytics
The method for the demo check, the visual review.
SkillAFreshness: A★ 5Claude Code +9 - 0.613score
converse-recheck-premise
zookanalytics
Converse's premise re-check and moot/benign visit close-out.
SkillAFreshness: A★ 5Claude Code +9 - 0.610score
converse-hold
zookanalytics
Converse's demand-gate hold (safety-critical).
SkillAFreshness: A★ 5Claude Code +9
Signals
- Stars
- 5
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Oct 17, 2026 (12 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/zookanalytics/gc-toolkit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from zookanalytics
- 0.620score
review-correctness
zookanalytics
The method for the correctness check, the standing review of whether a change is correct and safe as merged.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
review-pm
zookanalytics
The method for the PM check — the product lens on a change, reviewed by a peer to the author rather than an order-taker.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
work
zookanalytics
Use when you have to say that something needs doing, carry out a decision about who does it, or change work already asked for.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
learning-distill
zookanalytics
The promotion-judgment rubric for the feedback-learning loop — use when you are the mol-feedback-distiller judging pending feedback observations into…
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
prs
zookanalytics
Use when something has to happen to an open pull request or its anchor bead.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
review-arch
zookanalytics
The method for the arch check — the Architect, steward and gatekeeper of the repo's high-level architecture.
SkillAFreshness: A★ 5Claude Code +9
Cite this page
records skill. Agent Mart. https://agentmart.dev/skills/zookanalytics-records (last updated 2026-10-24)