paper-writing
Workflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → paper-write → paper-compile → auto-paper-improvement-loop to go from a narrative report to a polished, submission-ready PDF. Use when user says \"写论文全流程\", \"write paper pipeline\", \"从报告到PDF\", \"paper writing\", or wants the complete paper generation workflow.
79
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/skills-codex/paper-writing/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly communicates a specific multi-step paper writing pipeline, includes both Chinese and English trigger terms, and explicitly states both what the skill does and when to use it. The named sub-steps (paper-plan, paper-figure, etc.) make it highly distinctive from individual paper-related skills. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: orchestrates paper-plan → paper-figure → paper-write → paper-compile → auto-paper-improvement-loop, and describes the transformation from 'narrative report to a polished, submission-ready PDF'. The pipeline steps are explicitly named. | 3 / 3 |
Completeness | Clearly answers both 'what' (orchestrates a multi-step pipeline from narrative report to submission-ready PDF) and 'when' (explicit 'Use when' clause with specific trigger phrases and a general condition about wanting the complete workflow). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms in both English and Chinese: '写论文全流程', 'write paper pipeline', '从报告到PDF', 'paper writing', 'complete paper generation workflow'. These cover natural variations a user would actually say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive as it describes a specific multi-step orchestration workflow (paper-plan → paper-figure → paper-write → paper-compile → auto-paper-improvement-loop). The 'full pipeline' framing and specific sub-skill names clearly distinguish it from individual paper-related skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured orchestration workflow with excellent sequencing, checkpoints, and feedback loops, but it is far too verbose for a skill file. It re-explains what each sub-skill does in detail (which those sub-skills presumably already document), includes decorative elements like timeline tables and emoji-heavy checkpoint templates, and could be condensed to roughly 40% of its current size without losing any actionable information.
Suggestions
Drastically reduce the 'What this does' bullet lists under each phase to 1-2 lines max — the sub-skills document themselves; the orchestrator only needs to specify invocation, expected output, and checkpoint logic.
Remove or collapse the Typical Timeline table, Composing with Other Workflows section, and verbose checkpoint message templates into a compact reference — these consume significant tokens without adding actionable guidance.
Move the detailed Phase 6 report template to a separate REPORT_TEMPLATE.md file and reference it with a single line, rather than inlining the full markdown template.
Consolidate the Constants section and Key Rules into a single compact configuration block to reduce redundancy (e.g., AUTO_PROCEED is explained in both places).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines. It over-explains what each sub-skill does (Claude doesn't need 'What this does' bullet lists for skills it will invoke), includes unnecessary timeline tables, composition diagrams, and extensive checkpoint message templates that pad the content significantly. Much of this could be condensed to a fraction of the size. | 1 / 3 |
Actionability | The invocation commands for each phase are concrete and copy-paste ready (e.g., `/paper-plan "$ARGUMENTS"`), and the checkpoint templates give clear expected outputs. However, the skill mostly delegates to sub-skills without providing executable code itself — it's an orchestration script described in prose rather than actual executable logic, and some details like override syntax and constant configuration are somewhat vague. | 2 / 3 |
Workflow Clarity | The 6-phase pipeline is clearly sequenced with explicit checkpoints between phases, validation at Phase 4 (compilation must succeed before improvement loop), feedback loops in Phase 5 (review → fix → recompile × 2), and clear conditional logic (AUTO_PROCEED, HUMAN_CHECKPOINT). Error recovery is addressed (compilation retries, large file handling fallback). | 3 / 3 |
Progressive Disclosure | The skill references sub-skills (/paper-plan, /paper-figure, etc.) which provides natural decomposition, but the SKILL.md itself is monolithic — it inlines extensive details about what each sub-skill does rather than trusting the sub-skills to document themselves. The 'What this does' sections for each phase could be one-line summaries with references to the sub-skill docs. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Commit
dc00dfb
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.