feature-context-analysis SKILL.md skillA
feature-context-analysis from robsonkades/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add robsonkades/agent-skills/feature-context-analysis@git:20261016.c769bd8Pins git:20261016.c769bd8 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- robsonkades/agent-skills
- Path
skills/feature-context-analysis/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261016.c769bd8, committed Oct 16, 2026
- First version recorded
- Sep 6, 2026
- Size
- 10,255 bytes
- Repository stars
- 3
- License
- Apache-2.0
Reading the repository for one specific feature: which technologies and patterns are actually present, which components the feature can reuse, which questions the code has already answered, and — stated as findings rather than silence — which it has not. Use when a scoped feature needs repository evidence before clarification or technology selection, when it is about to be built in a style the codebase does not use, when "the project uses X" is being asserted without a path, when an…
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
# Feature Context Analysis ## Purpose Two things go wrong when this phase is skipped. The agent asks the user questions the code answers, spending the user's attention on facts and then having none left for the decisions only the user can make. Or the agent builds in a style the codebase does not use — a second HTTP client, a third validation approach, an abstraction that already exists two packages away — and the review is about the shape of the code rather than about whether the feature is right. The output is a **context report**: findings cite evidence and distinguish observation, inference and unresolved questions. "Not found in this sweep" is bounded search evidence, not proof of absence throughout the system. ## Workflow 1. **Scope the sweep to the feature.** Read what the feature will plausibly touch and one ring around it. A whole-repository survey costs more than it returns and produces a report nobody uses. If the feature is too ambiguous to select relevant paths, ask the smallest scope question; repository investigation does not require delaying a question only the user can answer. …
Read the whole file at its exact version.
How to install
mdr add robsonkades/agent-skills/feature-context-analysis@sha256:7e2d933b782e5e1eThe line at the top of this page pins the label git:20261016.c769bd8, 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_poq6cpepvmzfd5nm)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 6, 2026 and Oct 16, 2026, about one every 10 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261016.c769bd8 latest | 2026-10-16 | c769bd8 | 10,255 B | A | view · diff |
| git:20260927.9ecadfd | 2026-09-27 | 9ecadfd | 9,117 B | A | view · diff |
| git:20260923.832673e | 2026-09-23 | 832673e | 7,645 B | A | view · diff |
| git:20260911.37b054b | 2026-09-11 | 37b054b | 7,435 B | A | view · diff |
| git:20260906.e6ad4bd | 2026-09-06 | e6ad4bd | 6,925 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 (10255 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
robsonkades/agent-skills · 3 stars · license Apache-2.0 · pushed 2026-10-28 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_poq6cpepvmzfd5nm GET https://markdownregistry.com/api/v1/resolve?ref=robsonkades/agent-skills/feature-context-analysis GET https://markdownregistry.com/api/v1/blob/7e2d933b782e5e1ea08c57783a0894076b43aeeedef055de4753d0c111bb6463
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.