Claude Skill

doc-report

Summarize TeXada CLI checks, Studio repair candidates or local image/PDF transcription evidence. Use when the user needs an auditable account of changes, review decisions and remaining uncertainty, keeping OCR fidelity separate from syntax and compilation.

LLM Mart · 0 points · 0 views 0 listing impressions 0 install-command copies
Download caciniep-texada-studio-with-agentskills-skills_doc-report-ff0ae14.zip · 3 KB

Install

skills CLI npx skills add https://github.com/CacinieP/TeXada-Studio-with-agentskills/tree/main/skills/doc-report
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install caciniep-texada-studio-with-agentskills@llmmart
Git git clone https://github.com/CacinieP/TeXada-Studio-with-agentskills.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole caciniep/texada-studio-with-agentskills collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Quality Check Report

Select the evidence source

Workflow Existing records Report route
CLI node checks Run directory state.jsonl, available crops/, generated report.md Use the harness report generated for the relevant run_id; report-generation functions are in harness/docforensics/__main__.py
Studio .tex repair Studio data directory jobs/<job_id>/job.json and events.jsonl; authenticated job/status APIs Export the completed task's .audit.md from Studio, supplementing from persisted evidence when requested
Studio image/PDF transcription imports/<import_id>/source.<ext>, candidate.json, and (for PDF imports) pages/page-000001.png (pages/page-<6-digit>.png) Summarize the import record and human comparison with the source; OCR import has no separate built-in audit export

Use the configured Studio data directory, not an assumed repository-relative location: the local launcher defaults to the user's application data directory. Report generation must not rerun OCR, repair, compilation or the CLI pipeline merely to refresh a summary.

Report what actually happened

  • Identify the workflow, provider and model from recorded evidence. CLI and Studio formula-repair requests send formula text; Studio OCR sends page images to the local vision endpoint. Fixture repairs are offline test doubles, never measured model performance. Deterministic table checks have no model request.
  • For checks and repairs, include original and candidate text, source line or node, checker outcomes, attempted/rejected candidates and unresolved items. Preserve recorded reasons; missing responses after interruption are missing evidence. Bounded response excerpts may be truncated.
  • For Studio repair tasks, use result.original_sha256, candidate_sha256, edits, problems_after, trace, elapsed_seconds and compilation records when present. compile_ok and preview_ok are separate: a PDF may compile while image conversion fails. A NOT_CHECKED compilation was not a failed compilation.
  • Separate checker acceptance from human adoption. CANDIDATE_ACCEPTED records checker acceptance; USER_ACCEPTED/USER_REJECTED and top-level job review record the user's decision. Adoption into the editor is separate from saving a document. The current exported .audit.md includes result trace, but does not automatically include later review events from events.jsonl; inspect those records for a requested review audit.
  • For OCR, record source name/hash, import ID, configured model, page reported_model, content_sha256, imported page range and has_more_pages. Summarize unreadable spans and only the discrepancies actually compared against the original. requires_review: true marks a candidate, not completed review. The import record does not establish that the candidate was adopted or saved.
  • OCR pages[].raw_response is the cleaned transcription, not a complete raw transport response. Per-page usage may be absent; the import record has no repair-style model_calls or per-request event journal. Do not invent HTTP-attempt counts, elapsed time, OCR scores, bbox accuracy or confidence from page count/token metadata. Import source and field details are in the input contract.
  • Include CLI crops/ (or sources/ region snapshots) only when the files exist. Studio imports retain source.<ext> and, for PDF imports, persist verified per-page PNG evidence under imports/<import_id>/pages/page-000001.png (pages[].image_file, checked against recorded SHA256 and dimensions via LocalRuntime.get_page_evidence()). Distinguish Studio full-page import evidence from CLI node crops/; if an image file is missing or fails verification, mark the evidence unavailable instead of regenerating or fabricating it.
  • Keep OCR fidelity, syntax, compilation and mathematical correctness as separate conclusions. Successful checks or compilation do not establish faithful transcription or correct mathematics.

Calls and Skill evidence

Distinguish configured capabilities from operations recorded as executed. Report Skill mode and recorded skill_loaded/skill_sha256 evidence rather than assuming every named Skill ran. Studio OCR uses a fixed prompt and does not load doc-layout-parse; report generation is fixed code and does not load doc-report into a model.

For CLI request counts, use current-run PROVIDER_RESULT records and model_calls_known; unmatched starts or unknown counts mean a lower bound. An attempted request that times out may have reached the server, while completion remains unknown. For Studio, keep recorded repair model_calls scoped to that task; do not add earlier OCR requests to it or treat missing counts as zero.

Execution identity

CLI terminal reuse requires matching canonical input and execution-context hashes. A matching node identifier alone is insufficient. Reports must distinguish terminal results from skipped matching work and avoid counting resumed events as fresh quality measurements. Skill-content hashes identify the instructions loaded by the formula host; they do not prove better semantic accuracy.

Guardrails

Report generation must not trigger another model call or silently edit source files. Exclude credentials, allocated network details, and private document content from material intended for publication. Package existing evidence with relative paths when sharing a CLI run.

Files (texada-studio-with-agentskills)
  • evals
    • evals.json 1.6 KB
      Loading…
  • SKILL.md 5.7 KB
    ---
    name: doc-report
    description: Summarize TeXada CLI checks, Studio repair candidates or local image/PDF transcription evidence. Use when the user needs an auditable account of changes, review decisions and remaining uncertainty, keeping OCR fidelity separate from syntax and compilation.
    ---
    
    # Quality Check Report
    
    ## Select the evidence source
    
    | Workflow | Existing records | Report route |
    | --- | --- | --- |
    | CLI node checks | Run directory `state.jsonl`, available `crops/`, generated `report.md` | Use the harness report generated for the relevant `run_id`; report-generation functions are in `harness/docforensics/__main__.py` |
    | Studio `.tex` repair | Studio data directory `jobs/<job_id>/job.json` and `events.jsonl`; authenticated job/status APIs | Export the completed task's `.audit.md` from Studio, supplementing from persisted evidence when requested |
    | Studio image/PDF transcription | `imports/<import_id>/source.<ext>`, `candidate.json`, and (for PDF imports) `pages/page-000001.png` (`pages/page-<6-digit>.png`) | Summarize the import record and human comparison with the source; OCR import has no separate built-in audit export |
    
    Use the configured Studio data directory, not an assumed repository-relative location: the local launcher defaults to the user's application data directory. Report generation must not rerun OCR, repair, compilation or the CLI pipeline merely to refresh a summary.
    
    ## Report what actually happened
    
    - Identify the workflow, provider and model from recorded evidence. CLI and Studio formula-repair requests send formula text; Studio OCR sends page images to the local vision endpoint. Fixture repairs are offline test doubles, never measured model performance. Deterministic table checks have no model request.
    - For checks and repairs, include original and candidate text, source line or node, checker outcomes, attempted/rejected candidates and unresolved items. Preserve recorded reasons; missing responses after interruption are missing evidence. Bounded response excerpts may be truncated.
    - For Studio repair tasks, use `result.original_sha256`, `candidate_sha256`, `edits`, `problems_after`, `trace`, `elapsed_seconds` and compilation records when present. `compile_ok` and `preview_ok` are separate: a PDF may compile while image conversion fails. A `NOT_CHECKED` compilation was not a failed compilation.
    - Separate checker acceptance from human adoption. `CANDIDATE_ACCEPTED` records checker acceptance; `USER_ACCEPTED`/`USER_REJECTED` and top-level job `review` record the user's decision. Adoption into the editor is separate from saving a document. The current exported `.audit.md` includes result trace, but does not automatically include later review events from `events.jsonl`; inspect those records for a requested review audit.
    - For OCR, record source name/hash, import ID, configured `model`, page `reported_model`, `content_sha256`, imported page range and `has_more_pages`. Summarize unreadable spans and only the discrepancies actually compared against the original. `requires_review: true` marks a candidate, not completed review. The import record does not establish that the candidate was adopted or saved.
    - OCR `pages[].raw_response` is the cleaned transcription, not a complete raw transport response. Per-page `usage` may be absent; the import record has no repair-style `model_calls` or per-request event journal. Do not invent HTTP-attempt counts, elapsed time, OCR scores, bbox accuracy or confidence from page count/token metadata. Import source and field details are in [the input contract](../doc-layout-parse/references/vlm-prompts.md).
    - Include CLI `crops/` (or `sources/` region snapshots) only when the files exist. Studio imports retain `source.<ext>` and, for PDF imports, persist verified per-page PNG evidence under `imports/<import_id>/pages/page-000001.png` (`pages[].image_file`, checked against recorded SHA256 and dimensions via `LocalRuntime.get_page_evidence()`). Distinguish Studio full-page import evidence from CLI node `crops/`; if an image file is missing or fails verification, mark the evidence unavailable instead of regenerating or fabricating it.
    - Keep OCR fidelity, syntax, compilation and mathematical correctness as separate conclusions. Successful checks or compilation do not establish faithful transcription or correct mathematics.
    
    ## Calls and Skill evidence
    
    Distinguish configured capabilities from operations recorded as executed. Report Skill mode and recorded `skill_loaded`/`skill_sha256` evidence rather than assuming every named Skill ran. Studio OCR uses a fixed prompt and does not load `doc-layout-parse`; report generation is fixed code and does not load `doc-report` into a model.
    
    For CLI request counts, use current-run `PROVIDER_RESULT` records and `model_calls_known`; unmatched starts or unknown counts mean a lower bound. An attempted request that times out may have reached the server, while completion remains unknown. For Studio, keep recorded repair `model_calls` scoped to that task; do not add earlier OCR requests to it or treat missing counts as zero.
    
    ## Execution identity
    
    CLI terminal reuse requires matching canonical input and execution-context hashes. A matching node identifier alone is insufficient. Reports must distinguish terminal results from skipped matching work and avoid counting resumed events as fresh quality measurements. Skill-content hashes identify the instructions loaded by the formula host; they do not prove better semantic accuracy.
    
    ## Guardrails
    
    Report generation must not trigger another model call or silently edit source files. Exclude credentials, allocated network details, and private document content from material intended for publication. Package existing evidence with relative paths when sharing a CLI run.
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.