Agent skill

Status Update Writer

by aakashg in aakashg/pm-claude-skills

A skill your agent uses when the user asks to write a status update, weekly or monthly update, stakeholder update, project update, standup, status report, or QBR.

MITAuto-check passedProduct & Project Management

Install Status Update Writer

skills CLI
$ npx skills add aakashg/pm-claude-skills --skill status-update-writer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aakashg/pm-claude-skills status-update-writer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aakashg/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/status-update-writer .claude/skills/status-update-writer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
status-update-writer
GitHub stars
112
Token cost
~2.5k tokens
SKILL.md length
1,077 words
Files
2 (incl. references)
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user asks to write a status update, weekly or monthly update, stakeholder update, project update, standup, status report, or QBR.

  • Works in 3 steps: Read first → Gather → Calibrate to the audience
  • The user asks to write a status update
  • SKILL.md covers Step 0 — Read first, Constraints, Existence check and Step 1 — Gather, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Status Update Writer is an agent skill from aakashg/pm-claude-skills. Use when the user asks to write a status update, weekly or monthly update, stakeholder update, project update, standup, status report, or QBR. Do NOT use for writing a PRD or a retro doc — those need different structures.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/cadences.md`).

It sits in Product & Project Management, covering Customer success, Meeting notes and agendas and PRD writing. The repository describes itself as: 5 Claude Code skills for product managers. Drop them in your .claude/skills/ folder and go. The licence is MIT.

When your agent uses it

  • The user asks to write a status update
  • Stakeholder update
  • A retro doc — those need different structures

Example prompts

  • “/status-update-writer”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Read first
  2. Gather
  3. Calibrate to the audience

What it can do on your machine

Read from SKILL.md and the folder at commit 64deebf. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Status Update Writer loads about 2.5k tokens when it runs, and up to ~3.2k if it reads all its reference files. Until then it costs about 61 tokens; SKILL.md has 1,077 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aakashg/pm-claude-skills at commit 64deebf, republished under its MIT licence (© aakashg). 1,077 words, ~2,539 tokens.

Download SKILL.mdSave it as .claude/skills/status-update-writer/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
status-update-writer
description
Use when the user asks to write a status update, weekly or monthly update, stakeholder update, project update, standup, status report, or QBR. Do NOT use for writing a PRD or a retro doc — those need different structures.

Status Update Writer

Turn messy notes into a precise stakeholder update that stands alone without a follow-up meeting.

Step 0 — Read first

SourcePathWhat to extract
User's raw noteswhatever they pastedWhat actually shipped, real numbers, real dates, real names
Project contextCLAUDE.mdNorth star metrics, OKRs, company terminology, audience norms
Cadence formatsreferences/cadences.mdDaily / monthly / QBR variants of the base format
Last updateany prior update they nameWhat was promised last week — the delta is the story
Metrics sourcedashboard link or data they provideCurrent values only. Never estimate a metric.

If the user gave you no numbers, the update stays qualitative and you say so. Do not fill the gap.

Constraints

Mandatory.

  • Total update under 200 words for the weekly default.
  • Never fabricate progress. If the notes are thin, the update is thin.
  • Never hide bad news. It goes in the TL;DR, never at the bottom.
  • Never report activity as progress. "Had 6 meetings about the migration" is activity. "Migrated 40% of users at 0.3% error rate" is progress.
  • Every risk gets a mitigation. An unmitigated risk is just anxiety.
  • Every blocker gets a named owner and a date.
  • Every decision request gets a recommendation with reasoning.
  • Active voice only. "Team shipped the migration," not "The migration was completed."
  • No weasel words: roughly on track, mostly done, some concerns, making good progress.
  • Every line passes the "so what?" test for this specific audience. If cutting it changes nothing, cut it.
  • Never invent metrics. If the user did not give you a number, write [NEED: X].

Existence check

Before writing, verify:

  1. The work — what actually happened, in specifics.
  2. The audience — who reads this and at what altitude.
  3. The status — On Track, At Risk, or Blocked, and the evidence for it.

If two of three are missing, do not write. Ask for exactly those. An update written without knowing the audience gets the depth wrong in both directions — too technical for the board, too vague for the eng lead.

Step 1 — Gather

Ask:

  1. What project or initiative is this for?
  2. What happened this week? Paste notes, Slack threads, whatever you have — the messier the better.
  3. Who is the audience — CEO, VP Eng, cross-functional, skip-level, board?
  4. Is there bad news? If so, I will help frame it with a mitigation plan.

Never ask the user to organize their notes first. Extracting structure from mess is the job.

Step 2 — Calibrate to the audience

AudienceFocus onLeave out
CEO / C-suiteOutcomes, metrics, strategic implicationsImplementation details, technical decisions
VP / DirectorProgress against milestones, risks, resource needsCode-level detail, day-to-day tasks
Cross-functionalDependencies, timeline impacts, what they must knowInternal team dynamics, tech debt
Engineering leadTechnical blockers, architecture decisions, velocityBusiness context they already have
Skip-levelTeam impact, growth, winsMinutiae the direct manager handles
BoardMetrics, trajectory, market contextEverything operational

Default cadence is weekly. If the user says daily, monthly, quarterly, or QBR, switch to that format in references/cadences.md.

Output template

Exact fields, exact order. Omit only the sections marked optional.

**TL;DR** (2 sentences max)
[The whole update if they read nothing else. Most important thing first.
Bad news goes HERE, not below.]

**Status:** On Track | At Risk | Blocked

**Progress This Week**
- [What shipped or completed — never what was "worked on". Specific numbers.
  Links to PRs, docs, demos, dashboards where provided. Milestones called out.]

**Next Week**
- [What's planned, with owner. Dependencies on other teams flagged.
  Hard deadlines made visible.]

**Risks & Blockers**
- RISK: [description]. Likelihood: [H/M/L]. Impact: [what it costs].
  Mitigation: [the plan].
- BLOCKER: [what's blocked]. Owner: [who unblocks it]. Need by: [date].
[If none: "None currently." Never invent risks to fill the section.]

**Decisions Needed** (omit if none)
[What must be decided, who decides, by when, enough context to decide
without a meeting, and a recommendation with reasoning.]

**Metrics** (omit if the user provided no data)
- [Metric]: [current] (target: [target]) — [trend] — [one-line interpretation]

Status definitions: On Track = shipping on schedule, no blockers. At Risk = potential issues needing visibility, with a mitigation plan. Blocked = cannot proceed without a specific decision or action from a specific person.

Example

Input notes: "auth migration, we're at 40% web rollout now up from 10%, error rate 0.3%, load tests done handles 5x peak. mobile has a session bug hitting ~12% of users, jake's on it thinks thursday. launch was march 7, probably march 14 now. waiting on maria for QA signoff before we go past 40%. need to know if we ship web only."

Output:

TL;DR: Auth migration is at risk. We found a session handling bug
that affects 12% of users on mobile. Fix is in progress — ETA Thursday.
Launch pushed from March 7 to March 14.

Status: AT RISK

Progress This Week:
- Shipped auth migration to 40% of web users (up from 10% last week)
- Error rate holding at 0.3% — within our 1% threshold
- Completed load testing: system handles 5x current peak traffic

Next Week:
- Fix mobile session bug (owner: Jake, ETA Thursday)
- Expand to 100% of web users if mobile fix validates (owner: Sarah)
- Begin mobile rollout at 10% by Friday (owner: Sarah)

Risks & Blockers:
- RISK: Mobile session bug could have deeper root cause than initial
  diagnosis suggests. Likelihood: Medium. Impact: Additional 1-week
  delay. Mitigation: Jake is pairing with platform team on diagnosis.
  If not resolved by Thursday, we'll ship web-only and decouple mobile.
- BLOCKER: Need QA sign-off on load test results before expanding
  beyond 40%. Owner: Maria. Need by: Tuesday EOD.

Decision Needed:
Should we launch web-only on March 10 if the mobile bug isn't fixed,
or hold everything for March 14? I recommend launching web-only —
88% of auth traffic is web, and decoupling de-risks the mobile fix.
Need a decision from @VP-Eng by Wednesday.

The same notes written badly: "This week we continued working on the authentication project. The team has been making good progress. We're also looking into some issues that came up during testing but nothing major. On track for launch, will keep you posted." No specifics. "Some issues" is hiding a 12% failure rate. "On track" is false. The reader learns nothing and finds out about the slip later, which is how PMs lose trust.

Metrics, done badly and well:

Bad:
- Users: going well
- Revenue: looking good
- NPS: stable

Good:
- WAU: 142K (target: 150K) — flat for 3 weeks. Investigating whether
  the new onboarding friction is suppressing activation.
- Revenue: $1.2M MRR (+4% MoM) — on track for Q1 target of $1.3M
- NPS: 34 (down from 38 last month) — correlated with auth migration
  complaints. Expect recovery after bug fixes ship.
Show full SKILL.md (388 more words)Show less

Shortcuts Claude takes

What Claude might thinkWhy it's wrong
"The bad news reads harshly, I'll move it down"Burying the lead is how stakeholders find out too late. TL;DR or nowhere.
"The notes are thin, I'll add reasonable-sounding progress"Fabricated progress becomes a commitment the user has to defend. Keep it thin.
"I don't have the exact metric, I'll approximate"An approximate metric gets quoted as real in the next meeting. Write [NEED:].
"'Working on the migration' counts as progress"That is activity. Report what completed or explicitly say nothing shipped.
"A risk with no mitigation is still worth flagging"It is anxiety with no action. Either name a mitigation or downgrade it.
"The decision is obvious, they'll pick right"Always state the recommendation. Never make the reader redo your analysis.
"This is over 200 words but it's all useful"Length means the audience calibration is wrong. Cut to the audience's altitude.

Exit checklist

Not complete until every box is checked. Any [NEED: X], [date], [owner], or [metric] placeholder left in the update is an automatic unchecked box — fill it or ask the user for it before sending.

  • Existence check passed, or missing inputs requested
  • TL;DR is 2 sentences and contains the most important thing
  • If there is bad news, it is in the TL;DR
  • Status is exactly one of On Track / At Risk / Blocked
  • Every Progress bullet is an outcome, not an activity
  • Every Next Week item has an owner where known
  • Every risk has likelihood, impact, and a mitigation
  • Every blocker has a named owner and a date
  • Any decision request includes a recommendation with reasoning
  • Every metric has current value, target, trend, and interpretation
  • Under 200 words for weekly (see references/cadences.md for other targets)
  • No weasel words, no passive voice, no fabricated items
  • The update stands alone — no follow-up meeting needed to understand it
  • No placeholders remain

Next

  • If the update surfaced a decision that needs a written case → offer to draft the one-pager.
  • If a risk became a real slip → recommend re-running this skill at monthly cadence to reset expectations with the wider group.
  • If the update is going to a public or semi-public channel and needs a different register → recommend /linkedin-post-writer only for genuinely external wins.
  • If the metrics section keeps coming back empty → the gap is instrumentation, not writing. Say so.

© aakashg, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/status-update-writer of aakashg/pm-claude-skills.

  • SKILL.md
  • references/cadences.md

Open the folder on GitHubat commit 64deebf

Compare with similar skills

Status Update Writer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Status Update Writer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Status Update Writer this skillaakashg/pm-claude-skills112—~2.5kAutomated safety check: PassMIT
Pmstudio Commscoco-research/coco513—~1.2kAutomated safety check: PassCustom licence
Utility Pm Criticproduct-on-purpose/pm-skills716—~1.5kAutomated safety check: PassApache-2.0
Make Requirements Greatgnurio/nurijanian-skills124—~7.3kAutomated safety check: PassMIT
Tdoctornado-doc/tdoc103—~18kAutomated safety check: NotesAGPL-3.0
Gitea Workflowjwynia/agent-skills170—~3.8kAutomated safety check: PassMIT

Similar skills

  • Pmstudio Comms

    coco-research/coco

    Generate templated stakeholder communications from project context.

    513 GitHub stars~1.2k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Utility Pm Critic

    product-on-purpose/pm-skills

    Run adversarial review on a PM artifact via the pm-critic sub-agent.

    716 GitHub stars~1.5k tokensUpdated 2 days ago
    Product & Project ManagementAuto-check passed
  • Make Requirements Great

    gnurio/nurijanian-skills

    Review existing requirements or convert raw context into requirements that meet 18 quality characteristics (unambiguous, clear, cohesive, consistent, conformant, current, modifiable, traceable…

    124 GitHub stars~7.3k tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed
  • Tdoc

    tornado-doc/tdoc

    Use tdoc by default to create, edit, publish, or share any document, even when tdoc is not mentioned.

    103 GitHub stars~18k tokensUpdated today
    Product & Project ManagementAuto-check: notes
  • Gitea Workflow

    jwynia/agent-skills

    Orchestrate agile development workflows for Gitea repositories using the tea CLI.

    170 GitHub stars~3.8k tokensUpdated 7 mo ago
    Product & Project ManagementAuto-check passed
  • Ralph

    opentabs-dev/opentabs

    Plan work and generate ralph task files for autonomous execution.

    968 GitHub stars~157 tokensUpdated 7 days ago
    Product & Project ManagementAuto-check passed

More from aakashg/pm-claude-skills

  • Idea Validator

    aakashg/pm-claude-skills

    A skill your agent uses when the user asks to validate a product idea, stress-test an idea, evaluate whether an idea is good, or decide whether to build something.

    112 GitHub stars~2.3k tokensUpdated 2 mo ago
    Auto-check passed
  • Linkedin Post Writer

    aakashg/pm-claude-skills

    A skill your agent uses when the user asks to write, draft, or rewrite a LinkedIn post, turn notes or an article into a LinkedIn post, or fix a hook that is not landing.

    112 GitHub stars~1.8k tokensUpdated 2 mo ago
    Auto-check passed
  • Product Designer

    aakashg/pm-claude-skills

    A skill your agent uses when the user asks to review a design, critique a UI or mockup, give design feedback, or check a screen for usability and accessibility issues.

    112 GitHub stars~2.4k tokensUpdated 2 mo ago
    Auto-check passed
  • Prompt Engineer

    aakashg/pm-claude-skills

    A skill your agent uses when the user asks to improve, optimize, rewrite, debug, or shorten a prompt, or asks why a prompt is producing bad output.

    112 GitHub stars~2.2k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Status Update Writer

What does Status Update Writer do?

A skill your agent uses when the user asks to write a status update, weekly or monthly update, stakeholder update, project update, standup, status report, or QBR. Status Update Writer is an agent skill from aakashg/pm-claude-skills. Use when the user asks to write a status update, weekly or monthly update, stakeholder update, project update, standup, status report, or QBR.

When should I use Status Update Writer?

Status Update Writer fits situations like: the user asks to write a status update; stakeholder update; A retro doc — those need different structures.

How do I install Status Update Writer in Claude Code?

Run `npx skills add aakashg/pm-claude-skills --skill status-update-writer -a claude-code`. Or copy the skill folder (skills/status-update-writer in aakashg/pm-claude-skills) into .claude/skills/status-update-writer in your project. Claude Code loads it when a task matches its description.

How do I install Status Update Writer in Codex?

Run `npx skills add aakashg/pm-claude-skills --skill status-update-writer -a codex`. Or copy the skill folder (skills/status-update-writer in aakashg/pm-claude-skills) into .agents/skills/status-update-writer in your project. Codex loads it when a task matches its description.

Can I use Status Update Writer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aakashg/pm-claude-skills --skill status-update-writer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/status-update-writer, .gemini/skills/status-update-writer, .github/skills/status-update-writer and .opencode/skills/status-update-writer in your project.

What does Status Update Writer need to run?

SKILL.md names no scripts, command-line tools or credentials: Status Update Writer is instructions for the agent only.

Does Status Update Writer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Status Update Writer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Status Update Writer use?

Status Update Writer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Status Update Writer use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 643 tokens, read only when the agent opens those files.

What are the alternatives to Status Update Writer?

Skills that share tags, products or a category with Status Update Writer: Pmstudio Comms (coco-research/coco, 513 stars), Utility Pm Critic (product-on-purpose/pm-skills, 716 stars), Make Requirements Great (gnurio/nurijanian-skills, 124 stars) and Tdoc (tornado-doc/tdoc, 103 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Status Update Writer?

aakashg (a GitHub user) maintains it in aakashg/pm-claude-skills, which has 112 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on August 8, 2026.

Source: aakashg/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.