investigate-bug
Read-only diagnosis of a Slack bug from the tree and file bodies already fetched.
Skill by TribalScale
Chalk Labs
Need help deploying investigate-bug?
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/tribalscale-investigate-bug
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: 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. 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/investigate-bug
What's inside
- Skill name
investigate-bug- Description
- Read-only diagnosis of a Slack bug from the tree and file bodies already fetched. Cite only those files. Unknown cause is a valid result.
- License
- Apache-2.0
- Instructions
- 9 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Investigate bug Use this skill on the `investigate` stage of `bug_to_plan`. Read `input.tree` and `input.files` only. Do not clone the repo, search the rest of the tree, call `run_coding_backend`, open a pull request, post a status, or edit code. Cite only paths whose bodies are in `input.files`. If those files do not explain the bug, say the cause is unknown and name what is missing. Return `diagnosis` as a short markdown string.
From TribalScale/ts-harness, Apache-2.0.
More from TribalScale/ts-harness
- 0.600score
program-builder
TribalScale
Draft a new program (workflow, program, and routing intent) from a person's description on the admin program builder page.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
source-work-order
TribalScale
Source adapter that fetches Work Orders from docs/planner and maps them to NormalizedDeliveryContext for verified-merge.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
prd-to-work-orders
TribalScale
Converts Product Requirements Documents (PRDs) into validated Feature Requirements Documents (FRDs), technical Blueprints, and agent-ready Work Orders through…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
verified-merge
TribalScale
Delivers a unit of work through scoping, implementation, local verification, PR review, CI, merge approval, and post-merge verification using a pluggable…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
implement-work-order
TribalScale
Implement one governed work order from docs/planner specs.
SkillAFreshness: A★ 2Claude Code +9 - 0.597score
prd-to-work-orders-governed
TribalScale
Governed-runtime PRD-to-Work-Orders for enterprise workflow dispatch (JSON artifacts, no manifest/filesystem).
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
governed-code-review
TribalScale
Governed code review of delivered PRs against the work order before the QA gate.
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
verified-merge-governed
TribalScale
Governed-runtime work-order delivery via run_coding_backend (OpenCode) and host git/gh.
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
bdd-acceptance
TribalScale
Derive and automate BDD/Gherkin acceptance scenarios from work orders and planning docs.
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
source-work-order-governed
TribalScale
Governed-runtime source adapter that reads Work Orders from planner JSON artifacts and maps them to NormalizedDeliveryContext for implement handoff.
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
governed-qa-gate
TribalScale
Governed QA gate that verifies delivered PRs against acceptance criteria before the human merge wait.
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
coding-practices
TribalScale
Mandatory TDD, verification, and root-cause debugging for governed work-order implementation.
SkillAFreshness: A★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 17, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/TribalScale/ts-harness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from TribalScale
- 0.600score
program-builder
TribalScale
Draft a new program (workflow, program, and routing intent) from a person's description on the admin program builder page.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
source-work-order
TribalScale
Source adapter that fetches Work Orders from docs/planner and maps them to NormalizedDeliveryContext for verified-merge.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
verified-merge
TribalScale
Delivers a unit of work through scoping, implementation, local verification, PR review, CI, merge approval, and post-merge verification using a pluggable…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
prd-to-work-orders
TribalScale
Converts Product Requirements Documents (PRDs) into validated Feature Requirements Documents (FRDs), technical Blueprints, and agent-ready Work Orders through…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
implement-work-order
TribalScale
Implement one governed work order from docs/planner specs.
SkillAFreshness: A★ 2Claude Code +9 - 0.597score
prd-to-work-orders-governed
TribalScale
Governed-runtime PRD-to-Work-Orders for enterprise workflow dispatch (JSON artifacts, no manifest/filesystem).
SkillAFreshness: A★ 2Claude 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 investigate-bug 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
investigate-bug skill. Agent Mart. https://agentmart.dev/skills/tribalscale-investigate-bug (last updated 2026-10-24)