SKILLEMALL.ai
GitHub ↗ RU Sign in

CC odl-fix

Procedure to fix an existing opendataloader-pdf GitHub issue and open a pull request. It analyzes the issue and makes sub-issues for extra problems. It reproduces the failure and, before the fix, writes a contract: the problem and the fix as tests on small synthetic samples. It fixes the problem, and a harness (scripts/fix_gates.py) computes from runs whether the work is done. It submits before/after evidence that anyone can run again. Use it when the user asks to work on, fix, or send a pull request for an opendataloader-pdf issue ("fix #123", "take issue 456 and open a PR"). Also use it to see which open issues wait for us ("which issues should I look at first"): code classes each issue from facts and from the state line that ends each issue post. Do not use it for new bug reports, reviews of other pull requests, or replies to review comments. The user approves each GitHub post.

opendataloader-project/opendataloader-pdf Claude Code author: opendataloader-project Apache-2.0 7 files · 4 scripts body ≈ 15 704 tokens Open the sourcegithub.com↗ analyzed 3 h ago

Procedure to fix an existing opendataloader-pdf GitHub issue and open a pull request.

As a process C 56/100 · Has gaps — References files that are not bundled: ../odl-review/scripts/fetch_attachment.sh, ../../../.github/ISSUE_TEMPLATE/bug_report.md, scripts/build-python.sh

ProcedureGitHubSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
86/100
safety, quality, tests
Safety 60%
94
Quality 40%
74
Run on models
none yet
Process rating
C
56/100
Has gaps
References files that are not bundled: ../odl-review/scripts/fetch_attachment.sh, ../../../.github/ISSUE_TEMPLATE/bug_report.md, scripts/build-python.sh
Tools and files w 18
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 6

✓ No critical or high findings

Medium and low: 6
  • low Secrets in code secret-high-entropy-token references/harness.md:30
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    {"id": "P1", "kind": "problem", "test": "Issu…est#backendHeaderAndFooterAreOutputWithIncludeHeaderFooter",
    quoted
  • low Secrets in code secret-high-entropy-token references/harness.md:32
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    {"id": "G1", "kind": "guard", "test": "Issu…est#backendHeaderAndFooterStayOutWithoutIncludeHeaderFooter",
    detector
  • low Secrets in code secret-high-entropy-token references/harness.md:34
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    {"id": "G2", "kind": "guard", "test": "Issu…est#headerItemsAtSeparatePlacesKeepTheBodyColumnOrder",
    detector
  • low Secrets in code secret-high-entropy-token SKILL.md:372
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    - **Location**: Put a unit test in the package of the defective code, under `src/test/java/org/opendataloader/pdf/` in `opendataloader-pdf-core` (or `-cli`). Put a test that processes one sample from
    detector
  • low Secrets in code secret-high-entropy-token SKILL.md:452
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    Evidence:  Issu…est (PDFBox sample: 2 tables, 4x3 each);
    placeholder
  • low Secrets in code secret-high-entropy-token SKILL.md:720
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)
    | 2 | PDF built in the test with PDFBox | Tables, fonts, damaged or encrypted files, images, scans, structure trees | `Issu…est`, `CidFontDetectionTest`, `ScannedPagePdf`, `Hybr
    detectortable

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 15704 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: ../odl-review/scripts/fetch_attachment.sh
  • warning missing-ref reference to a missing file: ../../../.github/ISSUE_TEMPLATE/bug_report.md
  • warning missing-ref reference to a missing file: scripts/build-python.sh
  • warning missing-ref reference to a missing file: scripts/build-node.sh
  • warning missing-ref reference to a missing file: scripts/test-node.sh
  • warning missing-ref reference to a missing file: scripts/bench.sh
  • warning missing-ref reference to a missing file: scripts/generate-options.mjs
  • warning missing-ref reference to a missing file: scripts/generate-schema.mjs
  • note edit-residue the text marks something as outdated (lines 827): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 56/100

Will not run. References files that are not bundled: ../odl-review/scripts/fetch_attachment.sh, ../../../.github/ISSUE_TEMPLATE/bug_report.md, scripts/build-python.sh
  • 0Tools and files. 8 referenced file(s) missing: ../odl-review/scripts/fetch_attachment.sh, ../../../.github/ISSUE_TEMPLATE/bug_report.md, scripts/build-python.sh
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 73 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 40Execution cost. Instruction body is 15704 tokens: crowds the task out of the window
  • 100Steps. 141 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 10 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 17 top-level sections: this looks like several domains in one skill
  • high The skill tells the model to perform an irreversible action with no human approval
  • low The response is described with custom markup (47 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +3Description length 893: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +2Single-language instructions
  • +5Description quotes 3 example trigger phrases
  • +4Description says when NOT to use the skill
  • +4Structure: 40 headings
  • +3Step-by-step instructions: 141 items
  • +4Has examples (38 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 2 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.