agentleFS
Sign inStart free
open-agent-poweropen-agent-power/open-knowledge-studio/.claude/skills/upstream-pr-remediation/SKILL.md

upstream-pr-remediation

Skill9 starsChanged 3 months agoMITView on GitHub

Implement only the approved blocking fixes for upstream Open Knowledge Studio PR 4. Use when addressing its Feishu safety, cross-platform CLI, git hygiene, and Raw protocol documentation review findings; do not push, create a PR, or call real Feishu.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Keep .oks/ ignored and add a regression test for candidate, run, and lock paths.

    line 14
  2. Distinctive:

    Add focused tests for all five requirements, including Linux/Windows resolver selection, missing-CLI lazy failure, default versus explicit …

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Upstream PR 4 remediation

Work only in the dedicated remediation worktree. Preserve unrelated uncommitted work in the primary checkout. Do not push, open a PR, use Feishu credentials, or call a real Base.

Required changes

  1. Keep .oks/ ignored and add a regression test for candidate, run, and lock paths.
  2. Provide one lazily called, shared Lark CLI resolver. Prefer LARK_CLI_EXE; support lark-cli.cmd/.exe on Windows and lark-cli on Linux/macOS. Importing either Feishu module must not require a CLI installation.
  3. Make Feishu setup redact Base tokens by default. Add --show-credentials as the only opt-in full-display path. Default output and raised errors must not expose a Base token.
  4. Redact token/Bearer material and home-directory paths before writing a failed record's error text to Base; truncate after redaction.
  5. Restore a concise compatibility contract in the Raw protocol document: v0.1 invariants, v0.1-to-v0.2 mapping, reader compatibility, and migration route. Keep connector schemas and capability manifests as the v0.2 authority.

Required evidence

Add focused tests for all five requirements, including Linux/Windows resolver selection, missing-CLI lazy failure, default versus explicit credential display, error redaction, and the ignore contract. Run the full test suite and git diff --check.

Handoff

Return a concise report with: changed files, each review item and its test, full test command/result, unresolved non-blocking review suggestions, and risks. Do not commit, push, reply to GitHub, or resolve review threads.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free