fit-review SKILL.md skillA
fit-review from davidteren/intent-engineering is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add davidteren/intent-engineering/fit-review@git:20261009.55f76eePins git:20261009.55f76ee in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- davidteren/intent-engineering
- Path
plugins/expectation-fit/skills/fit-review/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261009.55f76ee, committed Oct 9, 2026
- First version recorded
- Oct 9, 2026
- Size
- 21,045 bytes
- Repository stars
- 3
- License
- MIT
Review code changes through the expectation-fit lenses (predictability, convention, simplicity, experience, and architecture on supported frameworks) — surfacing surprise, non-idiomatic patterns, needless complexity, UX gaps, and structural anti-patterns. Default (interactive) mode applies safe, verified fixes and commits on a clean tree (never pushes); mode:agent reports JSON only. Use on a PR, branch, or local changes before merging.
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
# Expectation Fit — Code Review
Reviews a diff for **surprise**: code that doesn't behave the way a reasonable
developer or user expects, fights convention, adds needless complexity, or skips UX
essentials. Fans out the applicable lenses as parallel sub-agents (the four universal
lenses, plus architecture on a supported framework), merges and confidence-gates their
findings, and writes a report. This is the runtime complement
to the principle docs under `${CLAUDE_PLUGIN_ROOT}/resources/`.
Grok users: this skill is the Claude orchestrator. There is also the optional Grok
workflow in the source repository (not shipped with the plugin): a subset, with the
report in scratch and no apply.
## Argument parsing
Parse `$ARGUMENTS`; strip recognized tokens before treating the remainder as a PR
number/URL or branch.
`out:`, `prior:` and `lenses:` are shared tokens, defined once in
`${CLAUDE_PLUGIN_ROOT}/references/config-resolution.md` (Shared tokens). Their rows below
list only this skill's difference.
| Token | Effect |
|-------|--------|
| `mode:agent` | Report-only; emit JSON (report-template "mode:agent"); skip the apply stage. Writes a report file only with `out:`. |
…Read the whole file at its exact version.
How to install
mdr add davidteren/intent-engineering/fit-review@sha256:fe354cfd81862849The line at the top of this page pins the label git:20261009.55f76ee, 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_xnztizdva3xpgvtm)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, all committed on Oct 9, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261009.55f76ee latest | 2026-10-09 | 55f76ee | 21,045 B | A | view · diff |
| git:20261009.e1a8e27 | 2026-10-09 | e1a8e27 | 20,577 B | A | view · diff |
| git:20261009.ccd3209 | 2026-10-09 | ccd3209 | 20,432 B | A | view · diff |
| git:20261009.5c19224 | 2026-10-09 | 5c19224 | 19,991 B | A | view · diff |
| git:20261009.2085429 | 2026-10-09 | 2085429 | 19,723 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 (21045 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
davidteren/intent-engineering · 3 stars · license MIT · pushed 2026-10-09 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xnztizdva3xpgvtm GET https://markdownregistry.com/api/v1/resolve?ref=davidteren/intent-engineering/fit-review GET https://markdownregistry.com/api/v1/blob/fe354cfd8186284999963d74e04e46659363e020ebe5686f1a01890589945814
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.
More from davidteren/intent-engineering
Every file in davidteren/intent-engineering