to-report
Turn this session (or one part of it) into a plain-language report for a non-technical reader: progress report, change summary, how-to, or explainer.
Skill by placek
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/placek-to-report
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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/to-report
What's inside
- Skill name
to-report- Description
- Turn this session (or one part of it) into a plain-language report for a non-technical reader: progress report, change summary, how-to, or explainer.
- License
- MIT
- Instructions
- 130 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# To Report Like `to-agent`, but the reader is a **person**, not an agent: a product owner, a customer, a manager, a teammate who only follows this project from a distance. You are the one responsible for the work done in this session, reporting to someone with a stake in it but not in the code. Work from what is already in the conversation and its artifacts (commits, diffs, `.todo/` files, specs, ADRs). Do **not** interview the user about the subject: you were there. Synthesise. ## 1. Pin the send Ask at most one round, and only for what the user's request left open: - **Who is it for?** Name a person or role. "Stakeholders" is too vague: a customer and a product owner care about different things. - **What shape?** One of the shapes below. If the user described the purpose instead, pick the shape and say which. - **Which part?** The whole session, or one aspect of it (one feature, one decision, one problem). If the user passed arguments, treat them as the answers and skip the questions. ## 2. Write the headline first One sentence the reader would keep if they read nothing else. Then the **so-what**: why it matters to *them* (what they can now do, what changed for them, what it costs or saves). If you cannot write the headline, you do not yet know what you are reporting: reread the session. ## 3. Build the inverted pyramid Headline, so-what, body, then risks and asks, then detail. Cut from the bottom: if the reader stops halfway, the important part has already landed. - **Outcomes, not activities.** "Customers can now pay by invoice" beats "implemented the invoice module and its tests." What you did is supporting evidence, one line at most. - **Plain language.** Use the project's own words from `CONTEXT.md` (the vocabulary the reader already shares) and nothing from the code: no file paths, function names, ticket numbers, branch names, tool names, or acronyms without a gloss. If a technical term is unavoidable, explain it once in a parenthesis. - **Honest status.** State plainly what is done, what is partly done, and what is not started. If something went wrong or slipped, it goes near the top, not sandwiched between wins. Yellow that never changes is red. - **One explicit ask, or none.** If you need a decision, information, or a review, say exactly what and by when, with a recommendation. If nothing is needed, say "no action needed." - **No hedging, no selling.** Cut "just", "really", "exciting", "we might possibly". Calibrate: confident where the work is verified, plain about what is untested. ## 4. Shapes **Progress report** (where things stand): ``` # <Project or feature>: progress, <date> **Status:** On track / At risk / Off track **Headline:** <one sentence> ## Done - <outcome, in the reader's terms> ## In progress - <item>: <how far, what is left> ## Not started / dropped - <item>: <why, if it was dropped> ## Risks - <risk>: <what it would mean for the reader>; <what we are doing about it> ## Needs from you - <specific ask, by when, with a recommendation> (or "No action needed") ## Next - <what happens next, and when the next update comes> ``` **Change summary** (what is different now and why): ``` # <What changed> **Headline:** <one sentence> ## Before <how it worked or looked for the reader> ## After <how it works now; what they can do that they could not> ## Why <the reason the change was made, in the reader's terms, and any trade-off accepted> ## What stays the same <reassurance about what this did not touch> ## Anything to watch for <known limitations, follow-ups, or "nothing"> ``` **How-to** (instructions a reader can follow without help): ``` # How to <do the thing> <One paragraph: when you would do this and what you end up with.> ## Before you start - <what you need> ## Steps 1. <one action per step, in the reader's words, with what they should see afterwards> ## If something goes wrong - <symptom>: <what to do> ``` **Explainer** (documentation of how something works, for reference): ``` # <Topic> <What it is and why it exists, two or three sentences.> ## How it works <walk through it in the order the reader meets it, plain language, no internals> ## Terms - **<term>**: <one-line meaning> ## Common questions - **<question>?** <answer> ``` Adapt headings to the case; the structure matters more than the exact labels. ## 5. Cut, check, save
From placek/skills, MIT.
More from placek/skills
- 0.524score
refactor
placek
Safe, behaviour-preserving refactoring of a module or codebase in small test-gated steps.
SkillBFreshness: BClaude Code +9 - 0.521score
ship
placek
Run a feature end to end through the other skills: grill the idea, spec and ticket it, write failing acceptance tests, implement outside-in, verify, document…
SkillBFreshness: BClaude Code +9 - 0.499score
domain-modeling
placek
Build and sharpen a project's domain model.
SkillBFreshness: BClaude Code +9 - 0.499score
grilling
placek
Grill the user relentlessly about a plan, decision, or idea.
SkillBFreshness: BClaude Code +9 - 0.499score
prototype
placek
Build a throwaway prototype to answer a design question.
SkillBFreshness: BClaude Code +9 - 0.499score
code-review
placek
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding…
SkillBFreshness: BClaude Code +9 - 0.499score
codebase-design
placek
Shared vocabulary for designing deep modules.
SkillBFreshness: BClaude Code +9 - 0.499score
tdd
placek
Test-driven development.
SkillBFreshness: BClaude Code +9 - 0.496score
to-tickets
placek
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, saved as one markdown file per ticket…
SkillBFreshness: BClaude Code +9 - 0.496score
to-spec
placek
Turn the current conversation into a spec and save it to `.todo/`: no interview, just synthesis of what you've already discussed.
SkillBFreshness: BClaude Code +9 - 0.496score
improve-codebase-architecture
placek
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
SkillBFreshness: BClaude Code +9 - 0.488score
implement
placek
Implement a piece of work based on a spec or set of tickets.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 24, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/placek/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from placek
- 0.556score
delegate
placek
Route, run, verify, record and escalate any implementation work bigger than a surgical few-line edit, across the local coder subagent, Claude Code and…
SkillAFreshness: AClaude Code +9 - 0.548score
routing-mode
placek
Switch this session's routing between auto, Claude Code only, and local only.
SkillAFreshness: AClaude Code +9 - 0.534score
domain-modeling
placek
Build and sharpen a project's domain model.
SkillAFreshness: AClaude Code +9 - 0.534score
codebase-design
placek
Shared vocabulary for designing deep modules.
SkillAFreshness: AClaude Code +9 - 0.534score
grilling
placek
Grill the user relentlessly about a plan, decision, or idea.
SkillAFreshness: AClaude Code +9 - 0.534score
prototype
placek
Build a throwaway prototype to answer a design question.
SkillAFreshness: AClaude Code +9
Cite this page
to-report skill. Agent Mart. https://agentmart.dev/skills/placek-to-report (last updated 2026-10-24)