name: review-core
description: |
Triggers: scaffolding, evidence, reporting, analysis, core
Foundational workflow for preparing and structuring detailed reviews
(architecture, API, code quality).
Triggers: review workflow, structured review, review scaffolding, evidence capture,
review preparation, analysis framework, review template
Use when: starting any detailed review workflow, needing consistent structure
for capturing context and findings, ensuring comparable review outputs
DO NOT use when: quick catchup without formal review - use catchup.
DO NOT use when: diff-focused analysis - use diff-analysis.
Use this skill at the BEGINNING of any detailed review for consistent structure.
category: review-patterns
tags: [workflow, scaffolding, evidence, reporting, analysis]
dependencies: []
tools: []
usage_patterns:
- review-preflight
- workflow-scaffolding
- evidence-capture
complexity: intermediate
estimated_tokens: 1500
version: 1.3.7
Core Review Workflow
When to Use
- Use this skill at the beginning of any detailed review workflow (e.g., for architecture, math, or an API).
- It provides a consistent structure for capturing context, logging evidence, and formatting the final report, which makes the findings of different reviews comparable.
Activation Patterns
Trigger Keywords: review, audit, analysis, assessment, evaluation, inspection
Contextual Cues:
- "review this code/design/architecture"
- "conduct an audit of"
- "analyze this for issues"
- "evaluate the quality of"
- "perform an assessment"
Auto-Load When: Any review-specific workflow is detected or when analysis methodologies are requested.
Required TodoWrite Items
review-core:context-established
review-core:scope-inventoried
review-core:evidence-captured
review-core:deliverables-structured
review-core:contingencies-documented
Step 1 – Establish Context (review-core:context-established)
- Confirm
pwd, repo, branch, and upstream base (e.g., git status -sb, git rev-parse --abbrev-ref HEAD).
- Note comparison target (merge base, release tag) so later diffs reference a concrete range.
- Summarize the feature/bug/initiative under review plus stakeholders and deadlines.
Step 2 – Inventory Scope (review-core:scope-inventoried)
- List relevant artifacts for this review: source files, configs, docs, specs, generated assets (OpenAPI, Makefiles, ADRs, notebooks, etc.).
- Record how you enumerated them (commands like
rg --files -g '*.mk', ls docs, cargo metadata).
- Capture assumptions or constraints inherited from the plan/issue so the domain-specific analysis can cite them.
Step 3 – Capture Evidence (review-core:evidence-captured)
- Log every command/output that informs the review (e.g.,
git diff --stat, make -pn, cargo doc, web.run citations). Keep snippets or line numbers for later reference.
- Track open questions or variances found during preflight; if they block progress, record owners/timelines now.
Step 4 – Structure Deliverables (review-core:deliverables-structured)
- Prepare the reporting skeleton shared by all reviews:
- Summary (baseline, scope, recommendation)
- Ordered findings (severity, file:line, principle violated, remediation)
- Follow-up tasks (owner + due date)
- Evidence appendix (commands, URLs, notebooks)
- validate the domain-specific checklist will populate each section before concluding.
Step 5 – Contingency Plan (review-core:contingencies-documented)
- If a required tool or skill is unavailable (e.g.,
web.run), document the alternative steps that will be taken and any limitations this introduces. This helps reviewers understand any gaps in coverage.
- Note any outstanding approvals or data needed to complete the review.
Exit Criteria
- All TodoWrite items complete with concrete notes (commands run, files listed, evidence paths).
- Domain-specific review can now assume consistent context/evidence/deliverable scaffolding and focus on specialized analysis.
Troubleshooting
Common Issues
Command not found
Ensure all dependencies are installed and in PATH
Permission errors
Check file permissions and run with appropriate privileges
Unexpected behavior
Enable verbose logging with --verbose flag
1---2name: review-core3description: - Use this skill at the beginning of any detailed review workflow (e.g., for architecture, math, or an API).4---5
6---
7name: review-core
8description: |
9
10Triggers: scaffolding, evidence, reporting, analysis, core
11 Foundational workflow for preparing and structuring detailed reviews
12 (architecture, API, code quality).
13
14 Triggers: review workflow, structured review, review scaffolding, evidence capture,
15 review preparation, analysis framework, review template
16
17 Use when: starting any detailed review workflow, needing consistent structure
18 for capturing context and findings, ensuring comparable review outputs
19
20 DO NOT use when: quick catchup without formal review - use catchup.
21 DO NOT use when: diff-focused analysis - use diff-analysis.
22
23 Use this skill at the BEGINNING of any detailed review for consistent structure.
24category: review-patterns
25tags: [workflow, scaffolding, evidence, reporting, analysis]
26dependencies: []
27tools: []
28usage_patterns:
29 - review-preflight
30 - workflow-scaffolding
31 - evidence-capture
32complexity: intermediate
33estimated_tokens: 1500
34version: 1.3.7
35---
36
37# Core Review Workflow
38
39## When to Use
40- Use this skill at the beginning of any detailed review workflow (e.g., for architecture, math, or an API).
41- It provides a consistent structure for capturing context, logging evidence, and formatting the final report, which makes the findings of different reviews comparable.
42
43## Activation Patterns
44**Trigger Keywords**: review, audit, analysis, assessment, evaluation, inspection
45**Contextual Cues**:
46- "review this code/design/architecture"
47- "conduct an audit of"
48- "analyze this for issues"
49- "evaluate the quality of"
50- "perform an assessment"
51
52**Auto-Load When**: Any review-specific workflow is detected or when analysis methodologies are requested.
53
54## Required TodoWrite Items
551. `review-core:context-established`
562. `review-core:scope-inventoried`
573. `review-core:evidence-captured`
584. `review-core:deliverables-structured`
595. `review-core:contingencies-documented`
60
61## Step 1 – Establish Context (`review-core:context-established`)
62- Confirm `pwd`, repo, branch, and upstream base (e.g., `git status -sb`, `git rev-parse --abbrev-ref HEAD`).
63- Note comparison target (merge base, release tag) so later diffs reference a concrete range.
64- Summarize the feature/bug/initiative under review plus stakeholders and deadlines.
65
66## Step 2 – Inventory Scope (`review-core:scope-inventoried`)
67- List relevant artifacts for this review: source files, configs, docs, specs, generated assets (OpenAPI, Makefiles, ADRs, notebooks, etc.).
68- Record how you enumerated them (commands like `rg --files -g '*.mk'`, `ls docs`, `cargo metadata`).
69- Capture assumptions or constraints inherited from the plan/issue so the domain-specific analysis can cite them.
70
71## Step 3 – Capture Evidence (`review-core:evidence-captured`)
72- Log every command/output that informs the review (e.g., `git diff --stat`, `make -pn`, `cargo doc`, `web.run` citations). Keep snippets or line numbers for later reference.
73- Track open questions or variances found during preflight; if they block progress, record owners/timelines now.
74
75## Step 4 – Structure Deliverables (`review-core:deliverables-structured`)
76- Prepare the reporting skeleton shared by all reviews:
77 - Summary (baseline, scope, recommendation)
78 - Ordered findings (severity, file:line, principle violated, remediation)
79 - Follow-up tasks (owner + due date)
80 - Evidence appendix (commands, URLs, notebooks)
81- validate the domain-specific checklist will populate each section before concluding.
82
83## Step 5 – Contingency Plan (`review-core:contingencies-documented`)
84- If a required tool or skill is unavailable (e.g., `web.run`), document the alternative steps that will be taken and any limitations this introduces. This helps reviewers understand any gaps in coverage.
85- Note any outstanding approvals or data needed to complete the review.
86
87## Exit Criteria
88- All TodoWrite items complete with concrete notes (commands run, files listed, evidence paths).
89- Domain-specific review can now assume consistent context/evidence/deliverable scaffolding and focus on specialized analysis.
90## Troubleshooting
91
92### Common Issues
93
94**Command not found**
95Ensure all dependencies are installed and in PATH
96
97**Permission errors**
98Check file permissions and run with appropriate privileges
99
100**Unexpected behavior**
101Enable verbose logging with `--verbose` flag