tracedocs
Turn any codebase into an evidence-grounded documentation package (overview,
operation, deployment, learning, architecture, API/data, troubleshooting,
maintenance) plus a machine-readable index.json for AI agents. Every
operational/deployment claim cites a source file and a confidence label
(Verified / Inferred / Unknown / Needs confirmation); it never invents
deployment steps and records gaps instead.
Full skill, references, templates, and a validated sample output:
https://github.com/wxggzz/tracedocs (MIT).
When to Use This Skill
- Onboarding to, or documenting, an unfamiliar codebase
- Producing durable, in-repo docs for operation, deployment, and maintenance
- Preparing an AI-agent-ready knowledge handoff (with
index.json)
- Turning a repo into a study guide whose claims are traceable to source
What This Skill Does
- Analyzes the codebase (stack, scripts, entry points, env-var names, deploy
signals, tests).
- Builds an evidence map (source map, assumptions, generation log) with
confidence labels.
- Writes the Markdown manuals and an
index.json manifest; never invents
deployment steps.
- Runs a quality check (paths exist, commands sourced, no secret values, gaps
documented).
How to Use
Basic Usage
Use tracedocs to generate evidence-grounded study docs for this repository. Write the output to study-docs/.
Example
User: "Document ./my-app with tracedocs"
The skill scans the repo and writes a study-docs/ package (00-10 manuals +
index.json + _evidence/), citing each operational claim's source and
labelling its confidence - and explicitly noting anything it cannot verify
(for example, "no deployment configuration found in the repo").
1---2name: tracedocs3description: Turn any codebase into evidence-grounded Markdown docs plus a machine-readable index.json. Every claim cites its source; never invents deployment steps.4---5
6# tracedocs
7
8Turn any codebase into an evidence-grounded documentation package (overview,
9operation, deployment, learning, architecture, API/data, troubleshooting,
10maintenance) plus a machine-readable `index.json` for AI agents. Every
11operational/deployment claim cites a source file and a confidence label
12(Verified / Inferred / Unknown / Needs confirmation); it never invents
13deployment steps and records gaps instead.
14
15Full skill, references, templates, and a validated sample output:
16https://github.com/wxggzz/tracedocs (MIT).
17
18## When to Use This Skill
19
20- Onboarding to, or documenting, an unfamiliar codebase
21- Producing durable, in-repo docs for operation, deployment, and maintenance
22- Preparing an AI-agent-ready knowledge handoff (with `index.json`)
23- Turning a repo into a study guide whose claims are traceable to source
24
25## What This Skill Does
26
271. Analyzes the codebase (stack, scripts, entry points, env-var names, deploy
28 signals, tests).
292. Builds an evidence map (source map, assumptions, generation log) with
30 confidence labels.
313. Writes the Markdown manuals and an `index.json` manifest; never invents
32 deployment steps.
334. Runs a quality check (paths exist, commands sourced, no secret values, gaps
34 documented).
35
36## How to Use
37
38### Basic Usage
39
40```
41Use tracedocs to generate evidence-grounded study docs for this repository. Write the output to study-docs/.
42```
43
44## Example
45
46**User**: "Document ./my-app with tracedocs"
47
48The skill scans the repo and writes a `study-docs/` package (00-10 manuals +
49`index.json` + `_evidence/`), citing each operational claim's source and
50labelling its confidence - and explicitly noting anything it cannot verify
51(for example, "no deployment configuration found in the repo").
majiayu000