useless-report

Generates a developer-facing change report from a repository's current changes, commits, PR context, saved screenshots, and before/after visual evidence. Use when the user asks for a dev report, change report, report on modifications, before/after screenshot report, UI change report, PR summary with visuals, "rapport de dev", "rapport sur les modifications", or wants to send a report about what changed after development.

Generates a natural call preparation document — talking points, opening hook, key messages, objection responses, and closing ask — adapted to both the manager's archetype and the user's own communication persona. Not a script: a structured guide that sounds like you. Covers status calls, idea pitches, crisis management, and general check-ins. Use when the user says "I have a call with my manager", "help me pitch this idea", "I need talking points", "prepare me for this conversation", or "what do I say on this call".

Generates a Q&A preparation document from a manager report — all the questions the manager is likely to ask (based on their archetype), with prepared answers derived strictly from the report data. Includes "danger questions" (the ones that catch you off guard), objection responses, and a quick-reference cheat sheet. Output is a collapsible HTML file to review before a meeting or call. Use when the user asks "what will my manager ask?", "help me prepare for my meeting", "I have a review tomorrow", or "Q&A prep".

Persists every generated report to a local history store, tracks manager requests and TODOs across sessions, and generates a delta section comparing current work to previous commitments. Answers: "what did I promise last time?", "what's still open?", "what changed since my last report?". Runs automatically as part of weekly-report. Also invokable standalone to review history, list open manager requests, or generate a delta summary. Use when the user asks "what was outstanding from last week?", "what did my manager ask for?", "show me the diff since last report", or "what's still on my TODO list from Alice?".

One-shot orchestrator that produces complete manager-adapted reports from the current git repository. Installed once per project, it reads the project's .useless-report/config.yml to know which manager profiles to generate for — no questions asked on repeat runs. Supports multiple managers: one run generates one report per saved profile. Ingests git activity, GitHub PRs, and ticket references. Renders to markdown, HTML, email, and/or slides using the project's DESIGN.md brand tokens. Use this skill when the user asks "generate my weekly report", "status update for my boss", or any one-shot report request from inside a git repo.

Installe une GitHub Action dans le repo courant qui génère automatiquement un commentaire useless-report sur chaque Pull Request. À l'ouverture ou la mise à jour d'une PR, la CI lit les commits, détecte le profil manager configuré, génère le rapport adapté via l'API Claude, et le poste comme commentaire sur la PR. Use this skill when the user asks for "CI integration", "auto-comment on PRs", "GitHub Action for reports", or "automate the report on every PR".

Analyzes a manager's communication style from messages, emails, Slack threads, PR comments, or meeting notes and outputs a structured communication profile: archetype name, confidence score, observed evidence, recommended communication strategy, and what to avoid. Use this skill when the user pastes manager messages and wants to adapt their communication, when preparing a status report that needs to land well, when starting the useless-report workflow, or any time the user asks "how should I write this for my manager", "what kind of manager is this", or "how does my boss communicate". Also triggers on "my manager always asks for...", "my boss never reads...", "my manager wants everything in meetings", or similar complaints about upward communication friction. This is the entry point for the entire useless-report workflow.

Converts a markdown manager report (the output of any useless-report generate-* skill) into an email-safe HTML file with fully inlined CSS — compatible with Gmail, Outlook, Apple Mail, and any webmail. No CSS variables, no external resources, no JavaScript. Colors and typography derived from DESIGN.md if present (tokens inlined as literal values, not CSS variables). Use this skill when the user wants to send the report directly by email, asks for "email-ready", "copy-paste into Gmail", "forward to my team", or needs a format that survives email client rendering. Triggers after any generate-* skill when the output destination is an email client.

Converts a markdown manager report (the output of any useless-report generate-* skill) into a standalone styled HTML file ready to email, share, or save. Includes embedded CSS derived from the project's DESIGN.md brand tokens — no hardcoded themes, no external dependencies. If no DESIGN.md is found, runs the generate-design flow first. Use this skill when the user wants to send a report by email, share a polished version, generate a printable artifact, or asks for "the HTML version", "make it look nice", "I need to send this to my boss", "format this for email". Triggers after any generate-* skill when the user wants a more polished output.

Converts a markdown manager report (the output of any useless-report generate-* skill) into a Marp-compatible slide deck — markdown with frontmatter that can be rendered to PDF, PPTX, or HTML slides via marp-cli. Visual style is derived entirely from the project's DESIGN.md brand tokens — no hardcoded themes. If no DESIGN.md is found, runs the generate-design flow first. Use this skill when the user wants a presentation version of their report, asks for "slides", "a deck", "PowerPoint", "something for the meeting", or needs to present findings to a steering committee or all-hands. Triggers after any generate-* skill when the user mentions a presentation context.

Generates a brief, high-signal update for an ambiguity-tolerant manager — someone who gives short approvals, delegates decisions, and doesn't need detail to feel confident. Use this skill after running useless-report:classify-manager-style and getting an ambiguity_tolerant profile, or directly when your manager always says "yeah just run with it", "lgtm", or "I trust your judgment". Also triggers when the user needs a short weekly check-in, a minimal FYI update, or wants to avoid over-reporting to a manager who doesn't need the detail.

Generates a detailed, structured weekly report for a control-oriented manager — the kind who asks for breakdowns, wants to review decisions before they're executed, and prefers options with explicit recommendations. Use this skill after running useless-report:classify-manager-style and getting a control_oriented profile, or directly when you know your manager fits the "Can you send me a quick detailed breakdown?" pattern. Also triggers when the user wants to write a weekly status update for a micromanager, when they want to preempt follow-up questions, or when they say things like "my manager always wants details" or "my boss needs to approve everything".

Generates a deadline-first status update for a deadline-reactive manager — someone who leads every conversation with delivery dates, interprets uncertainty as a threat to the timeline, and wants to know if the deadline is safe before anything else. Use this skill after running useless-report:classify-manager-style and getting a deadline_reactive profile, or directly when your manager always asks "are we going to make it?", "what's blocking us?", or "do we need to cut scope?". Also triggers when the user needs to write an urgent status update, communicate a deadline risk, or provide a delivery-focused progress report.

Génère ou valide un fichier DESIGN.md (standard Google Labs / Stitch, avril 2026) à partir de la charte visuelle de l'entreprise. Accepte n'importe quelle combinaison d'entrées : URL du site corporate, fichiers CSS/SCSS/tokens.json, screenshot, description textuelle — ou rien du tout, auquel cas un design générique professionnel est généré. Utilisé automatiquement par format-as-html et format-as-slides quand aucun DESIGN.md n'est présent. Déclencher directement avec /useless-report:generate-design pour initialiser la charte d'un nouveau projet.

Generates a fully self-contained update for a low-context manager — someone who frequently misses threads, asks for recaps, and can't be assumed to remember what was discussed last week. Use this skill after running useless-report:classify-manager-style and getting a low_context profile, or directly when your manager often says "remind me", "what did we decide?", or "I must have missed this". Also triggers when the user needs to write an update that should be readable by someone with no prior context, or when they're updating a manager who has been out or is juggling too much.

Generates a formal, fully-traced weekly report for a process-heavy manager — someone who wants everything tracked, documented, and cross-referenced with tickets or systems of record. Use this skill after running useless-report:classify-manager-style and getting a process_heavy profile, or directly when your manager asks "is this in JIRA?", "can you document this?", or "I need this for the quarterly review". Also triggers when the user needs a traceability-heavy report, an audit-ready summary, or a formal activity log with ticket references.

Generates a quality-first report for a quality-maximalist manager — someone who asks about test coverage, edge cases, and completeness before approving work, and who hesitates to ship without evidence that the unhappy paths were considered. Use this skill after running useless-report:classify-manager-style and getting a quality_maximalist profile, or directly when your manager always asks "did we consider all the edge cases?" or "what's our test coverage?". Also triggers when the user needs to justify readiness for release, document what was tested, or communicate known gaps with acceptable rationale.

Generates a stability-first weekly update for a risk-sensitive manager — someone who focuses on what could go wrong before acknowledging what went right and needs reassurance before approving changes. Use this skill after running useless-report:classify-manager-style and getting a risk_sensitive profile, or directly when your manager always asks "are we sure about this?", "what's the rollback plan?", or "have we stress-tested this?". Also triggers when the user says their manager is anxious about production changes, needs a risk-focused update, or always wants to know the contingency plan.

Generates a polished, forward-looking brief for a stakeholder-oriented manager — someone who frames everything in terms of external perception, needs material they can forward or present, and asks for "talking points" and "key messages" rather than technical details. Use this skill after running useless-report:classify-manager-style and getting a stakeholder_oriented profile, or directly when your manager asks for a summary they can share with a VP or steering committee. Also triggers when the user needs to write a management update that will be forwarded, presented, or used in a meeting they won't attend.

Generates a pre-meeting brief for a synchronous-first manager — someone who prefers live conversations over written updates, responds to messages by scheduling calls, and makes better decisions in real-time dialogue than async reading. Use this skill after running useless-report:classify-manager-style and getting a synchronous_first profile, or directly when your manager always says "let's jump on a call" instead of replying in writing. Also triggers when the user needs to prepare for a one-on-one, send a pre-meeting brief that will actually be read, or communicate something important to a manager who doesn't engage with long written updates.

Generates an alignment-first update for a volatile-priority manager — someone who frequently changes direction mid-sprint, introduces new priorities that override previous agreements, and doesn't always connect new requests to existing work in flight. Use this skill after running useless-report:classify-manager-style and getting a volatile_priority profile, or directly when your manager often says "actually, forget what I said last week" or redirects work without acknowledging the change. Also triggers when the user needs to show what was originally agreed, what changed, and how the team adapted — without expressing frustration.

Reads git history from the current repository to extract structured engineering activity for a given period — commits, files touched, contributors, branches, and ticket references found in commit messages. Use this skill when the user wants to generate a manager report from real git data, asks "what did we ship this week", "summarize the recent activity", "what's been happening in this repo", or before any useless-report generate-* skill when working inside a git repository. Also triggers when the user mentions weekly status, sprint summary, or wants to feed actual repo activity into the useless-report pipeline rather than typing a summary manually. Outputs a structured fact base ready to feed into any generate-* skill.

Fetches pull request and issue activity from GitHub for the current repository using the gh CLI. Extracts PR titles, status, review state, linked issues, and recent comments for a given period. Use this skill when the user wants to enrich a useless-report manager update with PR-level activity (not just commits), when they ask "summarize the PRs from this week", "what got merged", "what's still open", or before generating a manager report that benefits from PR context. Also triggers on "pull requests this sprint", "issue activity", or when working in a GitHub-hosted repository and wanting more than just git log data. Requires the gh CLI to be installed and authenticated.

Extracts ticket references (Jira, Linear, GitHub issues) from git commits and PRs in the current repository, then optionally enriches each ticket with title and status if the appropriate CLI is configured (jira-cli, linear-cli, gh). Use this skill when the user wants their manager report to include ticket-level traceability, when their commits use AUTH-184 / BILL-77 / LIN-99 patterns and they want those expanded into readable summaries, or before generating a process- heavy or control-oriented report that benefits from ticket detail. Triggers on "what tickets did we close", "expand the JIRA references", "show me the Linear items".