Skip to content

zrwangems/dsh-zrwang-plugin / ars/skills/academic-paper

academic-paper

Flagged

学术论文写作:按 IMRaD 或领域结构成稿,含大纲、论证地图、双语摘要、图表与题注、引用格式转换、返修与逐条回复、AI 使用声明。Triggers: write a paper, academic paper, paper outline, revise paper, reviewer comments, rebuttal, citation check, abstract | 写论文, 论文大纲, 修改论文, 审稿意见, 返修, 审稿回复, 引文核对, 写摘要。

FileKindSize
SKILL.mdskill md65.4 KB
_shared/ARCHITECTURE.mdmarkdown51.7 KB
_shared/MODE_REGISTRY.mdmarkdown6.7 KB
_shared/agents/compliance_agent.mdmarkdown9.4 KB
_shared/artifact_reproducibility_pattern.mdmarkdown9.8 KB
_shared/benchmark_report.schema.jsonconfig2.7 KB
_shared/benchmark_report_pattern.mdmarkdown8.8 KB
_shared/bibliographic_integrity_signals.mdmarkdown8.1 KB
_shared/collaboration_depth_rubric.mdmarkdown11.5 KB
_shared/compliance_checkpoint_protocol.mdmarkdown8.9 KB
_shared/compliance_report.schema.jsonconfig8.1 KB
_shared/contracts/README.mdmarkdown54.7 KB
_shared/contracts/activity/adjudication_activity_input.schema.jsonconfig18.5 KB
_shared/contracts/activity/adjudication_activity_store.schema.jsonconfig18.7 KB
_shared/contracts/audit/audit_jsonl.schema.jsonconfig5.4 KB
_shared/contracts/audit/audit_sidecar.schema.jsonconfig8.4 KB
_shared/contracts/audit/audit_verdict.schema.jsonconfig5.4 KB
_shared/contracts/audit/cross_document_consistency_advisory.schema.jsonconfig20.4 KB
_shared/contracts/audit/cross_document_consistency_advisory_draft.schema.jsonconfig23.4 KB
_shared/contracts/audit/cross_document_source_manifest.schema.jsonconfig6.3 KB
_shared/contracts/audit/tortured_phrase_advisory.schema.jsonconfig30.9 KB
_shared/contracts/audit/tortured_phrase_snapshot.schema.jsonconfig4.9 KB
_shared/contracts/audit/tortured_phrase_snapshot_manifest.schema.jsonconfig7.3 KB
_shared/contracts/capability/stage_capability_matrix.jsonconfig23.5 KB
_shared/contracts/claim_standing/candidate_ledger.schema.jsonconfig23.1 KB
_shared/contracts/claim_standing/query_plan.schema.jsonconfig12.7 KB
_shared/contracts/claim_standing/query_plan_v1_1.schema.jsonconfig20.3 KB
_shared/contracts/claim_standing/retrieval_input.schema.jsonconfig14.4 KB
_shared/contracts/claim_standing/stance_record.schema.jsonconfig11.7 KB
_shared/contracts/claim_standing/transmission_ledger.schema.jsonconfig7.6 KB
_shared/contracts/cross_model/codex_citation_receipt.schema.jsonconfig4.7 KB
_shared/contracts/cross_model/codex_citation_request.schema.jsonconfig986 B
_shared/contracts/cross_model/promotion_bakeoff_sealed_commitment.schema.jsonconfig1.5 KB
_shared/contracts/cross_model/promotion_bakeoff_sealed_reveal.schema.jsonconfig1.5 KB
_shared/contracts/degradation_registry.jsonconfig42.5 KB
_shared/contracts/evaluator/full.jsonconfig6.3 KB
_shared/contracts/evidence/claim_registry.schema.jsonconfig2.3 KB
_shared/contracts/evidence/claim_registry_coverage_report.schema.jsonconfig4.8 KB
_shared/contracts/evidence/evidence_row.schema.jsonconfig14.3 KB
_shared/contracts/evidence/evidence_row_v1_1.schema.jsonconfig11.4 KB
_shared/contracts/evidence/evidence_row_v1_2.schema.jsonconfig21.8 KB
_shared/contracts/evidence/evidence_row_v1_3.schema.jsonconfig10.7 KB
_shared/contracts/human_subjects/authority_profile_registry.schema.jsonconfig16.7 KB
_shared/contracts/human_subjects/committee_correspondence.schema.jsonconfig9.9 KB
_shared/contracts/human_subjects/content_coverage_advisory.schema.jsonconfig19.9 KB
_shared/contracts/human_subjects/irb_context_record.schema.jsonconfig12.1 KB
_shared/contracts/human_subjects/resolved_authority_context.schema.jsonconfig11.8 KB
_shared/contracts/human_subjects/review_pathway_rule_trace.schema.jsonconfig9.5 KB
_shared/contracts/human_subjects/review_pathway_trace_request.schema.jsonconfig4.8 KB
_shared/contracts/human_subjects/submission_packet_inventory.schema.jsonconfig8.5 KB
_shared/contracts/human_subjects/submission_packet_manifest.schema.jsonconfig32.2 KB
_shared/contracts/passport/audit_artifact_entry.schema.jsonconfig10.8 KB
_shared/contracts/passport/bibliographic_integrity_signal.schema.jsonconfig48.9 KB
_shared/contracts/passport/citation_provenance.schema.jsonconfig4.8 KB
_shared/contracts/passport/citation_verification_summary.schema.jsonconfig8.2 KB
_shared/contracts/passport/claim_audit_result.schema.jsonconfig7.8 KB
_shared/contracts/passport/claim_drift.schema.jsonconfig3.8 KB
_shared/contracts/passport/claim_intent_manifest.schema.jsonconfig6.6 KB
_shared/contracts/passport/constraint_violation.schema.jsonconfig3.6 KB
_shared/contracts/passport/excluded_source_entry.schema.jsonconfig1.7 KB
_shared/contracts/passport/experiment_alignment_result.schema.jsonconfig4.8 KB
_shared/contracts/passport/experiment_provenance_entry.schema.jsonconfig10.0 KB
_shared/contracts/passport/human_read_log.schema.jsonconfig3.8 KB
_shared/contracts/passport/inquiry_ledger_ref.schema.jsonconfig881 B
_shared/contracts/passport/literature_corpus_entry.schema.jsonconfig30.3 KB
_shared/contracts/passport/preregistration_artifact.schema.jsonconfig4.3 KB
_shared/contracts/passport/rejection_log.schema.jsonconfig3.3 KB
_shared/contracts/passport/reset_ledger_entry.schema.jsonconfig7.1 KB
_shared/contracts/passport/run_ledger.schema.jsonconfig8.0 KB
_shared/contracts/passport/standing_constraint_entry.schema.jsonconfig2.6 KB
_shared/contracts/passport/temporal_audit_results.schema.jsonconfig8.8 KB
_shared/contracts/passport/terminal_policies.schema.jsonconfig8.1 KB
_shared/contracts/passport/timeline.schema.jsonconfig4.7 KB
_shared/contracts/passport/uncited_assertion.schema.jsonconfig3.3 KB
_shared/contracts/passport/uncited_audit_failure.schema.jsonconfig4.4 KB
_shared/contracts/passport/user_attested_read_resolution.schema.jsonconfig3.2 KB
_shared/contracts/passport/version_records.schema.jsonconfig4.9 KB
_shared/contracts/patch/block_manifest.schema.jsonconfig2.1 KB
_shared/contracts/patch/legacy/v1_0/revision_patch.schema.jsonconfig5.3 KB
_shared/contracts/patch/revision_patch.schema.jsonconfig8.9 KB
_shared/contracts/pdf/pdf_content_classifier_diagnostic.schema.jsonconfig1.2 KB
_shared/contracts/pdf/pdf_content_classifier_worker.schema.jsonconfig2.2 KB
_shared/contracts/pdf/pdf_read_preflight.schema.jsonconfig6.8 KB
_shared/contracts/re_review/input_manifest.schema.jsonconfig7.6 KB
_shared/contracts/re_review/legacy/v1_0/input_manifest.schema.jsonconfig6.2 KB
_shared/contracts/re_review/legacy/v1_0/precommitment.schema.jsonconfig8.9 KB
_shared/contracts/re_review/legacy/v1_0/traceability.schema.jsonconfig34.2 KB
_shared/contracts/re_review/legacy/v1_0/verdict_record.schema.jsonconfig10.5 KB
_shared/contracts/re_review/precommitment.schema.jsonconfig8.6 KB
_shared/contracts/re_review/traceability.schema.jsonconfig37.7 KB
_shared/contracts/re_review/verdict_record.schema.jsonconfig10.5 KB
_shared/contracts/research_workflow/inquiry_branch_ledger.schema.jsonconfig17.0 KB
_shared/contracts/research_workflow/research_workflow_profile.schema.jsonconfig7.2 KB
_shared/contracts/research_workflow/research_workflow_profile_selection_receipt.schema.jsonconfig3.9 KB
_shared/contracts/review_target/constructive_review_findings.schema.jsonconfig7.0 KB
_shared/contracts/review_target/criteria_registry.schema.jsonconfig4.0 KB
_shared/contracts/review_target/review_criteria_binding_manifest.schema.jsonconfig7.9 KB
_shared/contracts/review_target/review_criteria_source_receipt.schema.jsonconfig5.6 KB
_shared/contracts/review_target/review_target_context.schema.jsonconfig4.5 KB
_shared/contracts/review_target/review_target_declaration.schema.jsonconfig4.6 KB
_shared/contracts/reviewer/full.jsonconfig3.7 KB
_shared/contracts/reviewer/methodology_focus.jsonconfig2.2 KB
_shared/contracts/reviewer/review_panel_provenance.schema.jsonconfig7.8 KB
_shared/contracts/reviewer/review_panel_provenance_carrier.schema.jsonconfig4.1 KB
_shared/contracts/reviewer/review_panel_provenance_input.schema.jsonconfig3.5 KB
_shared/contracts/revision/author_adjudication.schema.jsonconfig7.8 KB
_shared/contracts/revision/author_adjudication_input.schema.jsonconfig1.2 KB
_shared/contracts/revision/claim_strength_drift_disposition.schema.jsonconfig3.6 KB
_shared/contracts/revision/claim_strength_drift_disposition_input.schema.jsonconfig3.1 KB
_shared/contracts/revision/claim_strength_drift_findings.schema.jsonconfig4.2 KB
_shared/contracts/revision/claim_surface_manifest.schema.jsonconfig3.3 KB
_shared/contracts/revision/integrity_correction_authorization.schema.jsonconfig4.3 KB
_shared/contracts/revision/integrity_correction_authorization_input.schema.jsonconfig1.5 KB
_shared/contracts/revision/integrity_correction_list.schema.jsonconfig1.8 KB
_shared/contracts/revision/integrity_pass_receipt.schema.jsonconfig809 B
_shared/contracts/revision/revision_evidence_bundle.schema.jsonconfig4.9 KB
_shared/contracts/revision/revision_roadmap.schema.jsonconfig11.2 KB
_shared/contracts/submission/format_profile.example.yamlconfig971 B
_shared/contracts/submission/format_profile.schema.jsonconfig4.6 KB
_shared/contracts/submission/submission_verification_report.schema.jsonconfig10.3 KB
_shared/contracts/submission/venue_profile.schema.jsonconfig4.1 KB
_shared/contracts/writer/full.jsonconfig3.6 KB
_shared/cross_model_verification.mdmarkdown83.3 KB
_shared/description-original.mdmarkdown1.2 KB
_shared/dsh-runtime.mdmarkdown1.5 KB
_shared/evals_lift_report.schema.jsonconfig5.0 KB
_shared/ground_truth_isolation_pattern.mdmarkdown16.0 KB
_shared/handoff_schemas.mdmarkdown96.9 KB
_shared/human_subjects_authority_registry.jsonconfig49.5 KB
_shared/mode_spectrum.mdmarkdown5.2 KB
_shared/model_tiering.mdmarkdown12.6 KB
_shared/output_language_pair.mdmarkdown7.7 KB
_shared/policy_data/nature_policy.mdmarkdown3.9 KB
_shared/prisma_trAIce_protocol.mdmarkdown10.2 KB
_shared/raise_framework.mdmarkdown7.5 KB
_shared/references/authority_content_coverage_advisory_protocol.mdmarkdown14.0 KB
_shared/references/claim_standing_candidate_ledger_protocol.mdmarkdown19.2 KB
_shared/references/claim_strength_ladder.mdmarkdown5.5 KB
_shared/references/cross_document_consistency_advisory_protocol.mdmarkdown13.5 KB
_shared/references/evidence_row_protocol.mdmarkdown14.4 KB
_shared/references/firm_rules.mdmarkdown11.0 KB
_shared/references/human_subjects_authority_protocol.mdmarkdown13.1 KB
_shared/references/intent_clarification_protocol.mdmarkdown11.9 KB
_shared/references/irb_terminology_glossary.mdmarkdown12.4 KB
_shared/references/per_source_method_weaknesses.mdmarkdown4.2 KB
_shared/references/protected_hedging_phrases.mdmarkdown8.9 KB
_shared/references/psychometric_terminology_glossary.mdmarkdown8.7 KB
_shared/references/review_criteria_consumer_protocol.mdmarkdown10.3 KB
_shared/references/review_form_note.mdmarkdown11.3 KB
_shared/references/review_pathway_rule_trace_protocol.mdmarkdown8.3 KB
_shared/references/routing_core.mdmarkdown5.7 KB
_shared/references/submission_packet_manifest_protocol.mdmarkdown13.6 KB
_shared/references/word_count_conventions.mdmarkdown9.0 KB
_shared/research_workflow_profiles/field_general.jsonconfig1.2 KB
_shared/review_criteria_registry.jsonconfig11.5 KB
_shared/review_criteria_sources/msr-2027-technical-papers.2026-08-24.jsonconfig2.0 KB
_shared/review_criteria_sources/sigsoft-empirical-standards.2026-08-24.jsonconfig1.4 KB
_shared/sprint_contract.schema.jsonconfig19.0 KB
_shared/style_calibration_protocol.mdmarkdown6.9 KB
_shared/templates/codex_audit_multifile_template.mdmarkdown16.7 KB
agents/abstract_bilingual_agent.mdmarkdown12.5 KB
agents/argument_builder_agent.mdmarkdown11.5 KB
agents/citation_compliance_agent.mdmarkdown27.0 KB
agents/draft_writer_agent.mdmarkdown57.1 KB
agents/formatter_agent.mdmarkdown64.5 KB
agents/intake_agent.mdmarkdown26.1 KB
agents/literature_strategist_agent.mdmarkdown47.2 KB
agents/peer_reviewer_agent.mdmarkdown30.5 KB
agents/revision_coach_agent.mdmarkdown20.6 KB
agents/socratic_mentor_agent.mdmarkdown28.5 KB
agents/structure_architect_agent.mdmarkdown19.5 KB
agents/visualization_agent.mdmarkdown17.8 KB
examples/chinese_paper_example.mdmarkdown21.1 KB
examples/clinical_citation_verification_checklist.mdmarkdown4.4 KB
examples/clinical_epistemic_status_example.mdmarkdown6.6 KB
examples/commitment_ledger_example.mdmarkdown8.1 KB
examples/imrad_hei_example.mdmarkdown23.3 KB
examples/literature_review_example.mdmarkdown30.8 KB
examples/plan_mode_guided_writing.mdmarkdown34.3 KB
examples/revision_mode_example.mdmarkdown20.1 KB
examples/revision_recovery_example.mdmarkdown41.2 KB
examples/version_family_reconciliation_example.mdmarkdown3.8 KB
references/abstract_writing_guide.mdmarkdown13.2 KB
references/academic_writing_style.mdmarkdown8.2 KB
references/anti_leakage_protocol.mdmarkdown5.0 KB
references/apa7_chinese_citation_guide.mdmarkdown14.6 KB
references/apa7_extended_guide.mdmarkdown7.2 KB
references/changelog.mdmarkdown3.4 KB
references/citation_format_switcher.mdmarkdown8.0 KB
references/committee_correspondence_protocol.mdmarkdown7.0 KB
references/credit_authorship_guide.mdmarkdown14.3 KB
references/disclosure_mode_protocol.mdmarkdown54.5 KB
references/domain_evidence_profiles.mdmarkdown4.8 KB
references/failure_paths.mdmarkdown14.9 KB
references/funding_statement_guide.mdmarkdown12.5 KB
references/hei_domain_glossary.mdmarkdown7.4 KB
references/intro_title_rhetoric_guide.mdmarkdown9.3 KB
references/journal_submission_guide.mdmarkdown9.3 KB
references/latex_template_reference.mdmarkdown10.3 KB
references/mode_selection_guide.mdmarkdown18.3 KB

references/intro_title_rhetoric_guide.md

View on GitHub
> 输出语言(本 DSH 集成强制):所有面向用户的文字、稿件、摘要、评审与报告一律使用**简体中文**;英文术语与引文保持英文。文中的 `zh-TW` / `zh-tw-en` 只是上游语言代码与脚本参数,不代表要用繁体输出。用户明确要求其他语言时以用户为准。
>
> 多角色执行(评审团、十阶段流水线、角色扮演)必须使用 DSH 的 Agent Team 工具(`spawn_teammate`、`team_task_*`、`wait_agent`、`send_message`);当前会话看不到这些工具,说明用户没开 Agent Team,必须先提示用户开启,不得退化成单会话顺序扮演。
# Introduction & Title Rhetoric Guide

Used by `draft_writer_agent` (Step 1 pre-writing setup; Step 2 Introduction drafting; Step 3 title page assembly). Complements `references/paper_structure_patterns.md` (section architecture) and `references/abstract_writing_guide.md` (abstract composition). This guide covers the rhetorical work inside the Introduction and the title, not their placement.

---

## Part 1: Introduction Rhetoric (CARS Model)

The Introduction is a persuasion problem, not a summary problem. The reader must finish it convinced that (a) the territory matters, (b) something specific is missing or unresolved, and (c) this paper supplies it. Swales' Create A Research Space (CARS) model names these as three moves. Draft the Introduction move by move, in order.

### Move 1 — Establish the territory

Show that the topic is real, active, and consequential for this journal's readers.

**Steps** (use one or more):
- Claim centrality: why the field cares now (policy pressure, empirical anomaly, methodological turn)
- Make topic generalizations: what is broadly known or practiced
- Review prior work: the specific findings this paper builds on, synthesized rather than listed

**Discipline calibration**: empirical social science leans on centrality + prior findings; humanities may open with a text, case, or tension; engineering often opens with an application constraint.

**Anchor to materials**: every Move 1 claim about the field must trace to the Literature Search Report. Centrality claims without a citation are decoration and will be flagged at the integrity gate.

### Move 2 — Establish the niche

Show what is missing, unresolved, or contested. This is the pivot of the whole Introduction.

**Steps** (pick the one that matches the evidence):
- Indicate a gap: a population, setting, mechanism, or method prior work has not covered
- Counter-claim: prior findings conflict, and the conflict is unresolved
- Raise a question: known facts do not yet explain an observed pattern
- Continue a tradition: an established line of work licenses a next step

**The gap must be licensed by the review.** A gap statement is only as credible as the Move 1 synthesis that precedes it. If the annotated bibliography does not support "X has not been examined in Y," soften to what it does support ("evidence in Y remains limited to Z designs") or return to literature_strategist_agent for a targeted search. Never manufacture a gap.

**Avoid the universal-negative trap.** "No study has examined X" is an unverifiable claim and a common desk-reject irritant. Prefer scoped negatives tied to a documented search — "our search of [named databases], covering [period and design scope], identified no..." — or positive framings of the limit of current evidence.

### Move 3 — Occupy the niche

State what this paper does, in terms that mirror the niche just established.

**Steps** (in typical order):
- Announce purpose: one sentence, active, specific ("This study estimates..." not "This study aims to explore...")
- State RQs or hypotheses: verbatim the same RQs as the Paper Configuration Record, not paraphrases
- Preview contribution: what the reader will know afterward that they do not know now
- Outline structure: optional; many venues now cut it. Include only if the paper type template calls for it.

**Purpose-sentence discipline**: the purpose sentence is the most-quoted sentence in peer review. Draft it before drafting the rest of the Introduction, and check it answers the niche exactly. A Move 2 gap about "mechanism" answered by a Move 3 purpose about "prevalence" is a structural mismatch reviewers catch immediately.

### Proportions and length

- Introduction budget: typically 10-15% of body word count (respect the outline allocation from structure_architect_agent)
- Move 1 is the widest, Move 2 the shortest and sharpest, Move 3 concrete and unhedged about what was done (hedge findings, not actions)
- One move per paragraph is a safe default; Move 1 may take two

### Common failures

| Failure | Symptom | Fix |
|---------|---------|-----|
| Funnel too wide | Opens with "Since ancient times" scope | Start at the narrowest context that still shows stakes |
| Literature dump | Move 1 is a list of "A found X. B found Y." | Synthesize by theme or tension; cite in support of claims |
| Unlicensed gap | Move 2 asserts a gap the review never scoped | Rescope the gap or extend the search |
| Universal negative | "No study has ever..." | Scope it: database, period, design |
| Buried purpose | Move 3 purpose sentence hidden mid-paragraph | Lead the paragraph with it |
| Niche-purpose mismatch | Gap says mechanism, purpose says description | Rewrite the purpose to answer the stated gap |
| Findings leak | Full results narrated in the Introduction | Preview contribution type, keep numbers for Results (unless the discipline expects announced findings) |

---

## Part 2: Title Crafting

A title does three jobs: retrieval (search engines and databases), screening (a reader deciding whether to open the paper), and framing (setting the claim's ambition level). Draft 3-5 candidates at Step 3 assembly and select against the checklist below.

### Title anatomy

Most strong empirical titles carry: **key concept** (front-loaded) + **specifics** (population, setting, or mechanism) + optional **design signal** (e.g., "a longitudinal study," "evidence from X"). Word budget: aim for 15 words or fewer unless the venue's norms run longer.

### Title types

| Type | Shape | Norms and risks |
|------|-------|-----------------|
| Descriptive | "X and Y in Z context" | Safe default across disciplines; risk is blandness |
| Declarative | "X increases Y under Z" | Growing in high-impact science venues; the title becomes a claim, so it must carry the same hedging discipline as the abstract. Do not declare what the design cannot support |
| Interrogative | "Does X change Y?" | Accepted in social sciences and commentary; rare in engineering; some editors read it as hedging |
| Compound (colon) | "Catchy phrase: specific subtitle" | Common in humanities and social sciences; keep the pre-colon phrase informative, not merely cute |

### Checklist

- [ ] Front-loads the most important concept (first 3-4 words carry the topic)
- [ ] Contains the terms a searcher in this field would actually type (align with the abstract's keyword list; see `references/abstract_writing_guide.md`)
- [ ] 15 words or fewer, or a documented venue norm otherwise
- [ ] No abbreviations unless universally known in the field (DNA yes, HEI depends on venue)
- [ ] No throwaway openers: "A study of," "An investigation of," "Toward an understanding of"
- [ ] Claim level matches the design (no causal verbs on cross-sectional data)
- [ ] Specific enough to exclude papers it is not (a title that fits fifty papers screens none)
- [ ] Metaphor or wordplay, if any, is decoded by the subtitle

**Cross-check with the wording-pattern advisory**: several AI-typical RQ shells double as weak title shells, notably "A study of X and Y" (WP06), "A comparative study of X and Y" (WP17), and "Toward a framework for X" (WP18) from the Socratic mentor's reference table. If a candidate title matches one of those surface forms, treat it as a prompt to name the specific mechanism, site, or tension instead.

### Worked examples

| Weak | Stronger | Why |
|------|----------|-----|
| "A Study of AI and Higher Education" | "Generative AI in Programme-Level Quality Assurance: Evidence from 42 Taiwanese Universities" | Names the mechanism, population, and evidence base; survives the fifty-papers test |
| "Exploring the Impact of Feedback on Learning" | "Rubric-Anchored Peer Feedback and Revision Depth in First-Year Writing" | Replaces shell verbs with the actual instrument and outcome |
| "Toward a Framework for Teacher Wellbeing" | "Workload Rhythm, Not Workload Volume, Predicts Teacher Burnout: A Nine-Month Diary Study" | Declarative form carried by a design that can support it |

Examples are illustrative shapes, not field-verified claims; never reuse their content in a real paper.

---

## Provenance

Added for #500. The coverage gap (introduction rhetoric and title guidance) was surfaced by PR #485 (@lorenzo392), which proposed these topics inside a broader new-skill shape the suite declined. Content here was written fresh for this repo. Model source: the CARS model as introduced in Swales, J. M. (1990), *Genre Analysis: English in Academic and Research Settings*; a revised model appears in Swales, J. M. (2004), *Research Genres: Explorations and Applications*. This guide keeps the 1990 three-move structure and move labels but adapts the step inventory for this pipeline (e.g., Move 3 adds RQ/hypothesis restatement and contribution preview, and treats announcing full findings as a failure mode rather than a step).
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall