More screenshots
Works with the AI Agents you already use
Docs Generator: Documentation That Outlives the Session
Write task-oriented technical documentation with progressive disclosure — READMEs, API docs, architecture docs — plus formal reports where every finding traces to evidence.
$5
Docs Generator: Documentation That Outlives the Session
Example session with this skill installed
We just finished reverse-engineering an Android app and found a hardcoded API key in the native library. Write the formal report — it has to be usable by someone who was not in the room.
- Read your context and instructions
- Compiled the docs generator
Formal report — 2026-10-15_RE-apk-client-report.md (in the project directory, not in chat)
Target: com.example.app v2.3.1 (SHA-256 recorded). Methodology: static analysis (decompile, manifest review); dynamic (instrumented runtime, traffic capture).
Findings, each with evidence on its own line:
- F1 [High] API key hardcoded in native library. Evidence: libapp.so, offset 0x4a2c0 —
stringsoutput and the decompiled accessor. Impact: the key grants write access to the backend and ships in every install. Remediation: move to server-side issuance and rotate the exposed key. - Reproduction steps are exact: the commands, inputs, and environment are recorded so another analyst can re-derive F1 from the same binary.
Unresolved, stated plainly: certificate pinning bypass was not achieved on this build, so traffic capture is partial. That gap is in the report, not hidden — it is the next phase's starting point, not a secret.
IOCs and artifacts are listed at the end, each traceable to the analysis. Voice: direct, specific, no marketing adjectives — written for a competent peer who is busy. Rubric score: 7/8 — the remaining point is the review trigger, which is "when the app ships a new version," recorded in the maintenance note.
Connects securely to your tools. The creator never sees your data.
About this skill
Documentation exists so the next person — human or agent — does not have to redo your thinking. This skill covers two modes with one principle: lead with what the reader needs, disclose detail progressively, write for someone who was not in the room. Technical docs are structured by reader need (what is this, how do I run it, how do I use it, how do I contribute), layered so the quickstart works in five minutes and the reference detail waits for the reader who needs it, and kept next to the code in the same commit as the change.
Formal reports follow the shape of the work — reverse engineering, pen test, CTF writeup, malware analysis — with hard rules: evidence before claims, exact reproduction steps, finding separated from impact, unknowns named, and the dated filename in the project directory. A worked report skeleton shows a hardcoded API key finding with its evidence, impact, and remediation on four separate lines. A rubric gates delivery: below 6 out of 8, it is a draft with a filename, not documentation.
- It documents done work: a plan described as a result becomes fiction the team inherits, and the skill refuses to write it that way.
- It cannot manufacture evidence — a finding without an artifact is an opinion, and the report will say so rather than dressing it up.
- Stale docs are worse than no docs: when behavior changes and the doc does not, the skill's rule is to delete the stale page, not to leave a confident lie.
- The voice is deliberately plain and technical; marketing copy is out of scope and out of voice.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 days ago
Permissions
No special permissions declared or detected