PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mohitagw15856/pm-claude-skills --skill outcome-trackergit clone --depth 1 https://github.com/mohitagw15856/pm-claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mohitagw15856/pm-claude-skills/outcome-tracker)<a href="https://agentmods.dev/skills/mohitagw15856/pm-claude-skills/outcome-tracker"><img src="https://agentmods.dev/badge/skills/mohitagw15856/pm-claude-skills/outcome-tracker/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mohitagw15856/pm-claude-skills/outcome-tracker"><img src="https://agentmods.dev/badge/skills/mohitagw15856/pm-claude-skills/outcome-tracker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00100 | $0.01412 |
| Opus 5.5 | $0.00040 | $0.00565 |
| Sonnet 5.5 | $0.00020 | $0.00282 |
| Haiku 4.5 | $0.00010 | $0.00141 |
Grade A, and why
outcome-tracker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outcome Tracker Skill
Every prioritisation, forecast, and launch plan makes predictions — then everyone forgets to check them. This skill closes the loop: extract the predictions at decision time, park them somewhere durable, and score them against reality on a schedule. Over time it answers the question no one can answer today: which of our frameworks actually predict outcomes?
What This Skill Produces
- At decision time: a prediction record — each claim made falsifiable, with a metric, a direction/target, a check-by date, and a stated confidence
- At review time: an outcome scoring of due predictions (hit / miss / partial / unresolvable), with what was learned
- On demand: a calibration report — per-framework and per-confidence-band hit rates from the accumulated records
Required Inputs
Ask for (if not already provided):
- Mode — record (new decision), review (score due predictions), or calibrate (analyse the history)
- Record mode: the decision artifact (RICE table, forecast, launch plan, OKR set) and where records live (a
predictions/folder in the Brain, or a JSON/markdown file in the repo) - Review mode: the stored predictions plus current metric values for the due ones
- Calibrate mode: the prediction history (the calculator below reads it as JSON)
Making Claims Falsifiable (record mode)
Walk the artifact and force each implicit claim into this shape — a prediction that can't fill the row doesn't get recorded, it gets flagged as untestable:
| Field | Rule |
|---|---|
claim |
One sentence, future tense, about a measurable effect ("onboarding redesign lifts activation") |
metric |
The exact instrumented metric, with today's baseline |
predicted |
Direction + magnitude band ("+10-20% relative") — bands beat point estimates |
confidence |
0.5–0.95, from the author, recorded before the outcome is knowable |
check_by |
The date the effect should be visible if real; also the review trigger |
framework |
What produced the claim (rice-prioritisation, gut call, sales-forecasting-model…) — this is what calibration is about |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 96 lines · 100 tokens per session scan A fa407a932290
outcome-tracker is a skill published in the GitHub repository mohitagw15856/pm-claude-skills (1,449 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 1,412 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-12.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…