Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

Diligence-AI

@diligence-ai source repo

11 published skills

  1. ▌
    How We Work · diligence-ai
    Routes Diligence AI work to focused org skills for Linear workflow, task execution, pull-request delivery, client communication, changelogs, org-skill authoring, or the grilling and wayfinder working modes. Use at the start of a task, when blocked, or when unsure which team workflow applies. This is the lightweight index, not each full procedure.
    0
    installs
  2. ▌
    Task Execution · diligence-ai
    Guides Diligence AI execution choices for planning, reversible implementation, decision requests, and staying productive while blocked. Use when deciding whether to plan first, build a thin slice, ask the operator, or switch tasks. Do not use as the PR review or Linear status procedure.
    0
    installs
  3. ▌
    Writing Skills · diligence-ai
    Best practices for authoring, editing, and reviewing Agent Skills (SKILL.md files). Consult whenever someone asks to "write a skill", "create a skill", "improve a skill's description", "review a SKILL.md", or audit why a skill isn't triggering. Covers frontmatter, the description-as-trigger spec, progressive disclosure, body voice, testing, and anti-patterns. Do NOT trigger for ordinary docs, READMEs, or non-skill markdown.
    0
    installs
  4. ▌
    Linear Workflow · diligence-ai
    Keeps existing Linear work accurate while it moves from Todo through active work, review, blockers, and completion. Use when starting or resuming a Linear issue, changing its status, posting findings or blockers, or choosing the next ready task. Do not use to create a new issue; use create-linear-task instead.
    0
    installs
  5. ▌
    Client Changelog · diligence-ai
    Writes short, client-safe changelog entries for product fixes and updates. Use when asked for client update language, a client-facing fix summary, release notes, or changelog text. Do not use for internal engineering logs or technical postmortems. For general client messages, use client-communication.
    0
    installs
  6. ▌
    Create Linear Task · diligence-ai bundle
    Creates precise Linear issues from user-supplied requests, messages, notes, and attachments. Use when asked to create, file, log, or add one or more Linear tasks or tickets. Preserves stated facts, uploads supplied evidence, checks for duplicates and related blockers, and returns issue links. Do not use for implementing an issue or for updating an existing issue unless asked.
    0
    installs
  7. ▌
    Staging Browser QA · diligence-ai bundle
    Tests a completed feature in staging with agent-browser. Use when asked to "test this on staging", "QA this feature", "verify staging", "run browser QA", or "record a staging demo" after the feature reaches the staging branch. Confirms the deployed commit, runs focused browser checks, captures evidence, and prepares the human-QA handoff. Do not use for production deployment, load testing, or general release management.
    0
    installs
  8. ▌
    Org Skill Authoring · diligence-ai
    Creates, edits, validates, and publishes skills in the Diligence AI org-skills repository. Use when asked to create or update an org skill or change how-we-work. Commits and pushes org-skill changes straight to main, then applies them to the authoring environment or hands off that install.
    0
    installs
  9. ▌
    Client Communication · diligence-ai
    Drafts concise, client-ready messages such as status updates, blocker notices, handoffs, and recommendations. Use when text can reach a client or when asked to make a technical update client-friendly. Do not use for changelog or release note text; use client-changelog instead.
    0
    installs
  10. ▌
    External Code Review · diligence-ai bundle
    Runs an independent, read-only code review with the Claude Code CLI. Use when the operator says "review with Claude", "Claude review", "review with Opus", or "review with Fable". Selects the exact requested model and lets the paid review finish. Do not use for a normal review by the current coding agent.
    0
    installs
  11. ▌
    Pull Request Workflow · diligence-ai
    Runs the Diligence AI branch, pull-request, self-review, QA, human-review, and merge workflow. Use when creating a work branch or PR, preparing a PR for review, responding to review changes, deciding merge readiness, or merging. Do not use for a read-only review that will not change PR state.
    0
    installs