collaborate
Establish a pair-programming working agreement for the session.
Skill by corymhall
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/corymhall-collaborate
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: writing
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/collaborate
What's inside
- Skill name
collaborate- Description
- Establish a pair-programming working agreement for the session. Use explicitly at the start of a session or when asked to collaborate to reinforce repository-grounded shared thinking, concise communication, and high-signal writing without stopping clarification prematurely.
- License
- MIT
- Instructions
- 45 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Collaborate Act as a peer staff engineer pair-programming with the user. ## Solve Collaboratively 1. Inspect the repository and relevant examples before asking questions. Start by naming the current understanding, material open questions, and a light outline of the next step. 2. Prefer questions that change the outcome, scope, tradeoff, or implementation direction. Bring concrete options grounded in discovered context instead of asking broad, context-free questions. 3. Keep asking while important ambiguity remains. Do not stop because several questions have already been asked or because appearing decisive would be faster. 4. When implementation reveals new uncertainty, return to the conversation instead of silently guessing or expanding scope. 5. When rare or ambiguous cases add disproportionate complexity, present the smallest option that handles the evidenced or common case and a safe fallback for the remainder. Ask whether extra automation is worth its implementation and review cost. ## Communicate With Low Cognitive Load - Lead with the answer, code, command, diff, or decision. Do not begin with conversational filler, restate the request, or bury the result beneath process narration. - Prefer code-first micro-text to long explanation. Keep initial exploratory responses Slack-sized and do not generate unsolicited RFCs, schemas, exhaustive edge-case rebuttals, or implementation detail before the conversation needs them. Brevity must not hide material uncertainty. - Return a self-contained synthesis rather than internal reasoning or a progress autopsy. Use direct engineering language and remove generic claims about being robust, comprehensive, seamless, or thorough. ## Write High-Signal Documentation - Apply the compression test: if replacing a sentence with “be careful” or “follow best practices” loses little meaning, delete it or state the specific condition, consequence, mechanism, and action. - Keep operative guidance in the main path. Scope examples honestly, and move research history, raw evidence, and rare-case detail to an appendix when they would obscure the decision.
From corymhall/toolkit, MIT.
More from corymhall/toolkit
- 0.529score
harness-evaluation
corymhall
Evaluate real Pi and Codex sessions against centralized criteria for personal and repo-local skills, identify whether skills helped, were neutral, or made…
SkillBFreshness: BClaude Code +9 - 0.526score
triage-provider-issue
corymhall
Triage Pulumi provider issues from evidence to disposition or next action.
SkillBFreshness: BClaude Code +9 - 0.526score
skill-authoring
corymhall
Create, revise, de-slopify, or review Agent Skills while preserving useful behavior and requiring evidence for added prompt weight.
SkillBFreshness: BClaude Code +9 - 0.526score
go-development
corymhall
Implement and refactor Go where package design, abstractions, ownership, errors, concurrency, or Go-specific test seams require manual judgment.
SkillBFreshness: BClaude Code +9 - 0.524score
capture-decision-context
corymhall
Distill the current conversation into a durable, implementation-light decision note or compact GitHub issue draft that preserves motivation, evidence…
SkillBFreshness: BClaude Code +9 - 0.524score
commit
corymhall
Create a well-formed git commit from current changes using session history for rationale and summary; use only when the user explicitly asks to create or…
SkillBFreshness: BClaude Code +9 - 0.519score
aws-documentation-mcp
corymhall
Search, read, and cite official AWS documentation through the AWS Labs Documentation connection in executor.
SkillBFreshness: BClaude Code +9 - 0.479score
stage-terraform-provider-repro
corymhall
Stage durable Terraform-side repros for bridged-provider issues.
SkillCFreshness: CClaude Code +9 - 0.479score
stage-pulumi-provider-repro
corymhall
Stage durable Pulumi-side repros for provider issues.
SkillCFreshness: CClaude Code +9 - 0.479score
pulumi-upgrade-provider
corymhall
Automate Pulumi provider repo upgrades with the `upgrade-provider` tool.
SkillCFreshness: CClaude Code +9 - 0.479score
bridge-parity-investigation
corymhall
Investigate established Pulumi-vs-Terraform parity gaps with bridge cross-tests.
SkillCFreshness: CClaude Code +9 - 0.476score
neovim-plugin-development
corymhall
Implement, refactor, modernize, and debug Neovim plugins in Lua using official runtimepath/module-loading, startup/lazy-loading, keymap/autocmd, health…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 17, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/corymhall/toolkit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from corymhall
- 0.529score
harness-evaluation
corymhall
Evaluate real Pi and Codex sessions against centralized criteria for personal and repo-local skills, identify whether skills helped, were neutral, or made…
SkillBFreshness: BClaude Code +9 - 0.526score
triage-provider-issue
corymhall
Triage Pulumi provider issues from evidence to disposition or next action.
SkillBFreshness: BClaude Code +9 - 0.526score
go-development
corymhall
Implement and refactor Go where package design, abstractions, ownership, errors, concurrency, or Go-specific test seams require manual judgment.
SkillBFreshness: BClaude Code +9 - 0.526score
skill-authoring
corymhall
Create, revise, de-slopify, or review Agent Skills while preserving useful behavior and requiring evidence for added prompt weight.
SkillBFreshness: BClaude Code +9 - 0.524score
capture-decision-context
corymhall
Distill the current conversation into a durable, implementation-light decision note or compact GitHub issue draft that preserves motivation, evidence…
SkillBFreshness: BClaude Code +9 - 0.524score
commit
corymhall
Create a well-formed git commit from current changes using session history for rationale and summary; use only when the user explicitly asks to create or…
SkillBFreshness: BClaude Code +9
Cite this page
collaborate skill. Agent Mart. https://agentmart.dev/skills/corymhall-collaborate (last updated 2026-10-24)