Atlas / Skills / runkids / Skillshare Update Docs

Skillshare Update DocsSAFE

skills/runkids/skillshare-update-docs

๐Ÿ“š Sync skills, agents, MCP, plugins to all AI CLI tools with one command and simplify team sharing.

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
โ€”
Hosts
1 documented
License
MIT
Stars
2,749
01

Overview

๐Ÿ“š Sync skills, agents, MCP, plugins to all AI CLI tools with one command and simplify team sharing.

Read from source at commit 0d9340b2ca90OBSERVED ยท 2026-10-08
02

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
codexmentioned
03

What it tells the agent

The instruction file, verbatim from the audited commit โ€” this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: skillshare-update-docs
description: >-
  Update website docs to match recent code changes, cross-validating every flag
  against source. Use this skill whenever the user asks to: update documentation,
  sync docs with code, document a new flag or command, fix stale docs, or update
  the README. This skill covers all website/docs/ categories (commands, reference,
  understand, how-to, troubleshooting, getting-started) plus the built-in skill
  description and README. If you just implemented a feature and need to update
  docs, this is the skill to use. Never manually edit website docs without
  cross-validating flags against Go source first.
argument-hint: "[command-name | commit-range]"
metadata: 
  targets: [claude, universal]
---

Sync website documentation with recent code changes. $ARGUMENTS specifies scope: a command name (e.g., `install`), commit range, or omit to auto-detect from `git diff HEAD~1`.

**Scope**: This skill updates `website/docs/`, the built-in skill (`skills/skillshare/`), and `README.md`. It does NOT write Go code (use `implement-feature`) or CHANGELOG (use `changelog`).

Before acting, run `python3 scripts/ai-context.py documentation`. That topic is the source of truth for documentation ownership, code cross-validation and verification; this skill retains the update workflow.

## Workflow

### Step 1: Detect Changes

```bash
# Auto-detect recently changed code
git diff HEAD~1 --stat -- cmd/skillshare/ internal/

# Also check for structural changes that affect concept/reference docs
git diff HEAD~1 --stat -- internal/config/targets.yaml internal/audit/rules.yaml
```

Map changed files to affected documentation using this guide:

**Command docs** (`website/docs/reference/commands/`):
- `cmd/skillshare/<cmd>.go` โ†’ `website/docs/reference/commands/<cmd>.md`
- Flag changes, new subcommands, output format changes

**Concept docs** (`website/docs/understand/`):
- `internal/audit/` โ†’ `understand/audit-engine.md`
- `internal/sync/` โ†’ `understand/sync-modes.md`, `understand/source-and-targets.md`
- `internal/install/tracked.go` โ†’ `understand/tracked-repositories.md`
- `internal/config/` โ†’ `understand/declarative-manifest.md`
- `.skillshare/` project config changes โ†’ `understand/project-skills.md`
- `skills/skillshare/SKILL.md` format โ†’ `understand/skill-format.md`

**Reference docs** (`website/docs/reference/`):
- `internal/config/targets.yaml` โ†’ `reference/targets/`
- `internal/audit/rules.yaml` โ†’ `reference/commands/audit-rules.md`
- `reference/appendix/` for CLI quick-reference tables

**How-to guides** (`website/docs/how-to/`):
- New workflow patterns โ†’ `how-to/daily-tasks/`, `how-to/advanced/`, `how-to/recipes/`
- Sharing/org features โ†’ `how-to/sharing/`

**Troubleshooting** (`website/docs/troubleshooting/`):
- New error messages โ†’ `troubleshooting/common-errors.md`
- FAQ additions โ†’ `troubleshooting/faq.md`

**Getting started** (`website/docs/getting-started/`):
- Breaking changes to init/install flow โ†’ `getting-started/first-sync.md`
- Quick reference updates โ†’ `getting-started/quick-reference.md`

**Learn** (`website/docs/learn/`):
- New target integrations โ†’ `learn/with-<tool>.md`

### Step 2: Cross-Validate Flags

For each affected command:

1. Read the Go source to extract actual flags and behavior. Commands parse arguments by hand, so flags appear as string literals (`"--force"`) in the parse function of `cmd/skillshare/<cmd>.go`; `ss <cmd> --help` inside the devcontainer lists them too.

2. Read the corresponding doc page:
   ```
   website/docs/reference/commands/<cmd>.md
   ```

3. Compare and fix:
   - **New flags** in code โ†’ add to docs with usage example
   - **Removed flags** from code โ†’ remove from docs
   - **Changed behavior** โ†’ update description
   - **Every `--flag` in docs** must appear as a string literal in the command's source

### Step 3: Update Documentation

Apply changes following existing doc conventions:
- Match heading structure of neighboring doc pages
- Include CLI examples with expected output
- Keep flag tables consistent in format

### Step 4: Check Built-in Skill

If changes affect user-visible CLI behavior:

1. Read `skills/skillshare/SKILL.md`
2. Check if the built-in skill description needs updating
3. Verify description stays under 1024 characters (CodeX limit)

### Step 5: Check README

Review `README.md` for sections that may need updates:
- Recent Updates callout
- Why skillshare bullet points (5 selling points)
- Highlights section (core feature examples)

### Step 6: Build Verification

```bash
docker exec "$CONTAINER" bash -c 'cd /workspace/website && npm run build'   # as the Website Pages workflow builds
```

Confirm no broken links or build errors.

### Step 7: Report

List all changes made with rationale:
```
== Documentation Updates ==

Modified:
  website/docs/reference/commands/install.md
    - Added --into flag documentation
    - Updated install examples

  skills/skillshare/SKILL.md
    - Added --into to feature list (desc: 987/1024 chars)

Build: PASS (no broken links)
```

## Rules

Apply the `documentation` topic. Keep this adapter scoped to documentation; use the implementation or release workflows for other changes.
04

Trust audit

SAFEgrade B ยท trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryWARN
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (1)

MEDIUMInventory / provenance ยท inv.symlink ยท CWE-1104
.devcontainer/bin/dev-servers
.devcontainer/bin/dev-servers
Why it matters. link not followed

Gates applied: no_behavioural_pass.

Audited 2026-10-08 ยท audit v0.4.1 ยท source sha 0d9340b2ca90full audit observations/trust-audit/skill/runkids__skillshare-update-docs.json ยท Report an issue / request a re-scan
05

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-080d9340b2ca90SAFEB89first audit
06

Questions

What does the Skillshare Update Docs skill do?

๐Ÿ“š Sync skills, agents, MCP, plugins to all AI CLI tools with one command and simplify team sharing.

Is Skillshare Update Docs safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can Skillshare Update Docs access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

Which assistants does Skillshare Update Docs work with?

Its documentation mentions codex. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (0d9340b2ca90), read on 2026-10-08. The repository is watched, and a new audit runs when it changes โ€” this is the first audit.

Advertisement