measure-impact SKILL.md skillA
measure-impact from flagrare/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add flagrare/agent-skills/measure-impact@git:20261008.b2c58b8Pins git:20261008.b2c58b8 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- flagrare/agent-skills
- Path
plugins/flagrare/skills/measure-impact/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261008.b2c58b8, committed Oct 8, 2026
- First version recorded
- Oct 2, 2026
- Size
- 11,641 bytes
- Repository stars
- 13
- License
- none declared
Measure the impact of a piece of the user's work in a systematic way, at any stage. Before building, it makes an educated guess (a "bet"): a measured baseline, the closest comparable that can be measured, scaled by the right base, a range, a confidence level, and the saved query that will measure it. After launch, it re-runs that same query and gives a verdict (worked, didn't work, can't tell). For work already shipped, it finds the best number still available or says honestly that none exists.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Measure Impact
> **No em-dashes.** Nothing this skill writes may contain an em-dash; use a comma, colon, or parentheses instead. Enforced by a repo hook.
> **Plain words.** Use the plain names in `<plugin root>/lib/career/GLOSSARY.md` ("bet", "baseline", "check", "confidence level", "your written case"). The plugin root is two directories above this skill's base directory.
Impact claims without a method go wrong in three ways: targets that are wishes, numbers about the wrong thing, and checks nobody runs after launch. This skill runs the same method every time, saves what it found, and comes back to it.
**It never posts, sends or publishes anything.** It runs read-only queries only. Every write goes through `measurements.py` and the Write tool.
## Library
…Read the whole file at its exact version.
How to install
mdr add flagrare/agent-skills/measure-impact@sha256:60d075b9b621bb2dThe line at the top of this page pins the label git:20261008.b2c58b8, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_htjc5d62jukd66in)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Oct 2, 2026 and Oct 8, 2026, about one every day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261008.b2c58b8 latest | 2026-10-08 | b2c58b8 | 11,641 B | A | view · diff |
| git:20261002.d10b07e | 2026-10-02 | d10b07e | 11,205 B | A | view · diff |
| git:20261002.192e38c | 2026-10-02 | 192e38c | 11,090 B | A | view · diff |
| git:20261002.54f31a1 | 2026-10-02 | 54f31a1 | 10,835 B | A | view · diff |
| git:20261002.26ec8fa | 2026-10-02 | 26ec8fa | 10,692 B | A | view · diff |
| git:20261002.133eff4 | 2026-10-02 | 133eff4 | 10,608 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11641 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
flagrare/agent-skills · 13 stars · license none declared · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_htjc5d62jukd66in GET https://markdownregistry.com/api/v1/resolve?ref=flagrare/agent-skills/measure-impact GET https://markdownregistry.com/api/v1/blob/60d075b9b621bb2d9f5fbf6b05c7e3a2933377054511bcc123dd444c43243052
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.