research-evaluation SKILL.md skillA
research-evaluation from sfc-gh-eraigosa/dotfiles is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add sfc-gh-eraigosa/dotfiles/research-evaluation@git:20260808.ae8d6c9Pins git:20260808.ae8d6c9 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- sfc-gh-eraigosa/dotfiles
- Path
ai/skills/research-evaluation/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260808.ae8d6c9, committed Aug 8, 2026
- First version recorded
- Aug 8, 2026
- Size
- 8,553 bytes
- Repository stars
- 53
- License
- Apache-2.0
Discover and evaluate external tools/projects before adopting them, producing a consistent research dossier and (when the repo has one) a docs/mbo research design doc + tracking issue per target. Use when the user wants to "research X", "evaluate X before we adopt it", "look up X and tell me if it's useful", "start a research MBO for X", or gives a list of candidate tools to investigate — even a single target. Runs the nine-dimension rubric: (a) value to us, (b) setup cost + licensing, (c)…
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
# research-evaluation — evaluate before adopting Turn "should we use <tool>?" into a consistent, evidence-backed evaluation instead of an ad-hoc impression. Works for one target or a batch; generalizes to any repo. ## The rubric (all nine, every target) | Dim | Question | | :-- | :-- | | (a) **Value** | What is it worth *to us* — which of our real problems does it solve, and what do we already have that overlaps or conflicts? | | (b) **Setup cost & licensing** | Install steps, prerequisites, pain points; the exact license, commercial tiers, telemetry/data terms. | | (c) **Adversarial review** | The case AGAINST adopting: negatives, dangers, unknown pitfalls, failure modes, lock-in. Written to refute (a). | | (d) **Security & safety** | Known and unknown gotchas: what it executes, what data it touches/stores/sends, supply-chain surface, CVEs/advisories. | | (e) **Stability** | Likelihood it destabilizes our workflow or running services; maturity, breaking-change history, blast radius. | | (f) **Quality & support** | Maintenance signals **with the observation date**: stars, contributors/bus factor, release cadence, issue responsiveness, docs, last commit. | …
Read the whole file at its exact version.
How to install
mdr add sfc-gh-eraigosa/dotfiles/research-evaluation@sha256:0ea56610758c34c3The line at the top of this page pins the label git:20260808.ae8d6c9, 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_uyg43d42dqsdljga)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, all committed on Aug 8, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260808.ae8d6c9 latest | 2026-08-08 | ae8d6c9 | 8,553 B | A | view · diff |
| git:20260808.50c45db | 2026-08-08 | 50c45db | 6,702 B | A | view · diff |
| git:20260808.623abbc | 2026-08-08 | 623abbc | 5,759 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 (8553 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
sfc-gh-eraigosa/dotfiles · 53 stars · license Apache-2.0 · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_uyg43d42dqsdljga GET https://markdownregistry.com/api/v1/resolve?ref=sfc-gh-eraigosa/dotfiles/research-evaluation GET https://markdownregistry.com/api/v1/blob/0ea56610758c34c3f919b0d006cbd7cf7a70aa280377deebc04d6af112f351f6
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.