setup-matt-pocock-skills
Configure a repo's issue tracker, triage vocabulary, and domain-document layout for the engineering skills.
Skill by lstmemery
Chalk Labs
Need help deploying setup-matt-pocock-skills?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/lstmemery-setup-matt-pocock-skills
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
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. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/setup-matt-pocock-skills
What's inside
- Skill name
setup-matt-pocock-skills- Description
- Configure a repo's issue tracker, triage vocabulary, and domain-document layout for the engineering skills.
- License
- MIT
- Instructions
- 54 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (12)
- LOCAL-TICKETS.md
- SKILL.md
- VETTING.md
- openai.yaml · agents/
- domain.md
- issue-tracker-github.md
- issue-tracker-gitlab.md
- issue-tracker-local.md
- local-tickets.py · scripts/
- ticket_execution.py · scripts/
- ticket_planning.py · scripts/
- triage-labels.md
SKILL.md (first lines)
# Setup Avery Pocock's Skills Create or update the repo configuration consumed by the engineering skills: the issue tracker, five triage-role labels, and domain-doc layout/reading rules. Explore first, batch independent choices, then show a concrete configuration for review before applying it. ## Explore and select the instruction file Inspect existing remote/repo configuration, root `AGENTS.md` and `CLAUDE.md` (including any `## Agent skills` block), `CONTEXT.md`, `CONTEXT-MAP.md`, root/context ADR directories, `docs/agents/`, and `.scratch/` conventions. Check monorepo signals such as `pnpm-workspace.yaml`, package workspaces, or populated packages with their own source. **File selection:** edit `CLAUDE.md` if it exists; otherwise edit existing `AGENTS.md`. If neither exists, include which to create among the unresolved choices. When both exist, use `CLAUDE.md`; do not create a second file or overwrite surrounding user content. ## Settle only open choices Present findings and recommendations together so independent decisions can be answered in one reply. Reuse already established preferences. Follow up only on choices whose answers depend on that reply. - **Tracker:** propose GitHub for a GitHub remote, GitLab for a GitLab remote, or local Markdown when appropriate. For another tracker, obtain the user's workflow in a short paragraph. This selects `docs/agents/issue-tracker.md`. - **Triage vocabulary (always included):** recommend keeping `needs-triage`, `needs-info`, `ready-for-agent`, `ready-for-human`, and `wontfix`. If no accepted vocabulary exists, ask whether to keep these defaults as part of the same batch. Collect overrides only when the user wants different strings; reuse existing tracker labels rather than creating duplicates. - **Domain layout:** use single-context (root `CONTEXT.md` and `docs/adr/`) without asking when exploration settles it. Offer multi-context, with root `CONTEXT-MAP.md` and per-context documents, only when monorepo signals justify the choice. - **Instruction file:** ask which file to create only when neither candidate exists. ## Draft, review, and apply Load only the selected tracker seed: [GitHub](issue-tracker-github.md), [GitLab](issue-tracker-gitlab.md), or [local Markdown](issue-tracker-local.md). For another tracker, draft from the user's workflow. Use [triage-labels.md](triage-labels.md) and [domain.md](domain.md) for the always-required vocabulary and domain rules. Show the exact proposed contents of `docs/agents/issue-tracker.md`, `docs/agents/triage-labels.md`, `docs/agents/domain.md`, and the instruction-file block below. Let the user correct the concrete draft before writing; apply existing authorization and do not repeat settled questions. ```markdown ## Agent skills ### Issue tracker <One-line tracker summary>. See `docs/agents/issue-tracker.md`. ### Triage labels <One-line vocabulary summary>. See `docs/agents/triage-labels.md`. ### Domain docs <Single-context or multi-context summary>. See `docs/agents/domain.md`. ``` Update an existing block in place, preserving surrounding sections. Always write the triage doc and its sub-block. The domain configuration describes where future records belong; it does not require creating empty domain records. Done when the chosen instruction file and all three configuration docs agree with the reviewed choices, pointers resolve, and no duplicate block exists. Report the files and which engineering skills consume them. They can be edited directly; rerunning is useful for changing trackers or restarting configuration. When **adding or evaluating a candidate skill for the suite**, read [VETTING.md](VETTING.md). Routine repo setup does not load that branch. ## Local ticket operations For local Markdown tracker mechanics, use [LOCAL-TICKETS.md](LOCAL-TICKETS.md). It defines the shared command used by ticket publication, Wayfinder, and implementation closeout. It does not automate the setup choices above.
From lstmemery/skills, MIT.
More from lstmemery/skills
- 0.589score
orchestrator
lstmemery
Coordinate delegated coding, research, and everyday tasks across agent harnesses.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
retro
lstmemery
Review a named or current coding and orchestration session for evidence-backed improvements to an agent's environment.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
shopping
lstmemery
Research a concrete purchase or current offer.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
ticket-readiness
lstmemery
Review a specified ticket before implementation for current applicability, remaining acceptance, material assumptions, and directly related work.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
diagnosing-bugs
lstmemery
Diagnose bugs, failures, and performance regressions using an observed failure signal and targeted probes.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
grilling
lstmemery
Stress-test a plan, decision, or idea through a relentless interview when the user asks to be grilled.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
deep-research
lstmemery
Investigate broad comparisons, literature, landscapes, buy/build decisions, and high-stakes questions; use research for focused lookups.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
research
lstmemery
Answer focused questions from documents, APIs, or a few sources; route broad comparisons and high-stakes investigations to deep-research.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
domain-modeling
lstmemery
Resolve domain terms, scenarios, ownership, boundaries, context maps, and ADRs; routine vocabulary lookup stays in project docs.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
tdd
lstmemery
Use test-first development for features, fixes, and integration tests; test lists, tracer bullets, and red-green cycles.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
code-review
lstmemery
Review branches, PRs, fixed commits, or working changes against repository standards and the originating spec.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
herdr
lstmemery
Control Herdr panes, layouts, commands, and agents only when explicitly requested; requires HERDR_ENV=1.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 12, 2026 (19 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/lstmemery/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lstmemery
- 0.589score
orchestrator
lstmemery
Coordinate delegated coding, research, and everyday tasks across agent harnesses.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
retro
lstmemery
Review a named or current coding and orchestration session for evidence-backed improvements to an agent's environment.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
shopping
lstmemery
Research a concrete purchase or current offer.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
ticket-readiness
lstmemery
Review a specified ticket before implementation for current applicability, remaining acceptance, material assumptions, and directly related work.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
diagnosing-bugs
lstmemery
Diagnose bugs, failures, and performance regressions using an observed failure signal and targeted probes.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
grilling
lstmemery
Stress-test a plan, decision, or idea through a relentless interview when the user asks to be grilled.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get setup-matt-pocock-skills running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
setup-matt-pocock-skills. Agent Mart. https://agentmart.dev/skills/lstmemery-setup-matt-pocock-skills (last updated 2026-10-24)