deslop

Name: deslop
Author: thtskaran

16stars2forks

How to install deslop?

thtskaran/claude-skills/deslop

$npx -y skills add thtskaran/claude-skills --skill deslop

Installs into the current project.

Summary

Audit and harden existing codebases (especially AI-generated / vibe-coded ones) for production readiness. Use when the user asks to review, audit, clean up, harden, deslop, refactor, or fix quality issues across an existing codebase. Works in two phases — first a thorough multi-p

Files · 1

View on GitHub

SKILL.md

1	# Deslop — Code Hardening Skill
2
3	Systematically audit and harden an existing codebase for production. Designed for AI-generated ("vibe coded") codebases that work superficially but are fragile, sloppy, or insecure under real-world conditions.
4
5	This skill operates in two strict phases. Never mix them.
6
7	```
8	Phase 1: AUDIT → produces AUDIT.md (human-reviewable, machine-parseable)
9	Phase 2: FIX → consumes AUDIT.md → applies fixes in safety order
10	```
11
12	The user provides a codebase (directory path or repo). They may specify focus areas, exclusions, or constraints. If not specified, audit everything.
13
14	---
15
16	## Phase 1: AUDIT
17
18	MANDATORY before starting: Read the full audit checklist and format spec:
19	```
20	Read ~/.claude/skills/deslop/references/checklist.md # 15-category audit checklist with specific patterns
21	Read ~/.claude/skills/deslop/references/audit-format.md # Structured finding format for AUDIT.md
22	```
23
24	The audit runs five sequential passes. Each pass builds on the previous. Never skip a pass — thoroughness matters more than speed.
25
26	### Pass 0 — Reconnaissance
27
28	Map the codebase before judging anything. Do NOT write findings yet.
29
30	1. Generate file tree: `find . -type f \| head -500` or equivalent. Understand the shape.
31	2. Classify files: Source, tests, configs, migrations, infra, docs, generated, vendored.
32	3. Identify the stack: Language(s), framework(s), package manager, build system, runtime.
33	4. Build dependency map: Which files import from which. Use `grep -rn "import\\|require\\|from\\|include"` or language-specific tooling.
34	5. Identify entry points: Main files, route handlers, API endpoints, CLI entry points, event handlers.
35	6. Detect existing tooling: Check for `.eslintrc`, `pyproject.toml`, `tsconfig.json`, `.prettierrc`, `Makefile`, CI configs, etc.
36	7. Run available linters: If linters are configured, run them and capture output. If not, note this as a finding. Common commands:
37	- JS/TS: `npx eslint . --format json 2>/dev/null` or `npx tsc --noEmit 2>&1`
38	- Python: `python -m pylint */.py --output-format=json 2>/dev/null` or `python -m flake8 . 2>&1`
39	- Go: `go vet ./... 2>&1`
40	- Rust: `cargo clippy --message-format=json 2>/dev/null`
41	- If no linter is configured, skip — don't install new tooling unless asked.
42	8. Produce the codebase map: Write a structured summary to the top of `AUDIT.md`:
43	- Stack summary (language, framework, runtime)
44	- File count by category
45	- Module/directory architecture
46	- Entry points
47	- High-coupling modules (most imports in + out)
48	- Linter output summary (if available)
49
50	Output of Pass 0: The "Codebase Overview" section of `AUDIT.md`. No findings yet.
51
52	### Pass 1 — Patterns & Consistency
53
54	Scan for mechanical quality issues that don't require deep semantic understanding. Process file-by-file, prioritizing high-coupling modules first (from Pass 0's dependency map).
55
56	What to scan (load `~/.claude/skills/deslop/references/checklist.md` categories 8-14):
57	- Naming convention violations and inconsistencies
58	- DRY violations — duplicated logic blocks, copy-pasted code
59	- Dead code — unused functions, unreachable branches, commented-out code, unused imports
60	- Magic numbers and hardcoded values
61	- Missing type annotations (for typed languages)
62	- Inconsistent patterns (e.g., callbacks in one file, promises in another)
63	- KISS/YAGNI violations — unnecessary abstractions, premature optimization
64	- Dependency issues — unused deps, circular imports
65
66	Chunking strategy for large files (>500 lines): Read in function/class-sized chunks. Never split in the middle of a function. When analyzing a chunk, re-read the file's import header for context.
67
68	For each finding: Write it to `AUDIT.md` using the format from `~/.claude/skills/deslop/references/audit-format.md`.
69
70	### Pass 2 — Logic & Resilience
71
72	Trace critical paths through the code. This pass requires cross-file context.
73
74	Start from entry points identified in Pass 0. For each critical path:
75	1. Trace the happy path from input to output.
76	2. Then ask: what happens when each step fails?
77	3. Check every error handling point: is the error caught? Logged? Re-thrown? Swallowed?
78	4. Check edge cases: null/undefined inputs, empty collections, boundary values, concurrent access.
79	5. Check data validation at trust boundaries (user input, API responses, file reads, env vars).
80
81	What to scan (load `~/.claude/skills/deslop/references/checklist.md` categories 2-4):
82	- Correctness bu

People who liked this also viewed

6 picks

Type

deslop

16stars2forks

View on GitHub

How to install deslop?

thtskaran/claude-skills/deslop

$npx -y skills add thtskaran/claude-skills --skill deslop

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Deslop — Code Hardening Skill
2
3	Systematically audit and harden an existing codebase for production. Designed for AI-generated ("vibe coded") codebases that work superficially but are fragile, sloppy, or insecure under real-world conditions.
4
5	This skill operates in two strict phases. Never mix them.
6
7	```
8	Phase 1: AUDIT → produces AUDIT.md (human-reviewable, machine-parseable)
9	Phase 2: FIX → consumes AUDIT.md → applies fixes in safety order
10	```
11
12	The user provides a codebase (directory path or repo). They may specify focus areas, exclusions, or constraints. If not specified, audit everything.
13
14	---
15
16	## Phase 1: AUDIT
17
18	MANDATORY before starting: Read the full audit checklist and format spec:
19	```
20	Read ~/.claude/skills/deslop/references/checklist.md # 15-category audit checklist with specific patterns
21	Read ~/.claude/skills/deslop/references/audit-format.md # Structured finding format for AUDIT.md
22	```
23
24	The audit runs five sequential passes. Each pass builds on the previous. Never skip a pass — thoroughness matters more than speed.
25
26	### Pass 0 — Reconnaissance
27
28	Map the codebase before judging anything. Do NOT write findings yet.
29
30	1. Generate file tree: `find . -type f \| head -500` or equivalent. Understand the shape.
31	2. Classify files: Source, tests, configs, migrations, infra, docs, generated, vendored.
32	3. Identify the stack: Language(s), framework(s), package manager, build system, runtime.
33	4. Build dependency map: Which files import from which. Use `grep -rn "import\\|require\\|from\\|include"` or language-specific tooling.
34	5. Identify entry points: Main files, route handlers, API endpoints, CLI entry points, event handlers.
35	6. Detect existing tooling: Check for `.eslintrc`, `pyproject.toml`, `tsconfig.json`, `.prettierrc`, `Makefile`, CI configs, etc.
36	7. Run available linters: If linters are configured, run them and capture output. If not, note this as a finding. Common commands:
37	- JS/TS: `npx eslint . --format json 2>/dev/null` or `npx tsc --noEmit 2>&1`
38	- Python: `python -m pylint */.py --output-format=json 2>/dev/null` or `python -m flake8 . 2>&1`
39	- Go: `go vet ./... 2>&1`
40	- Rust: `cargo clippy --message-format=json 2>/dev/null`
41	- If no linter is configured, skip — don't install new tooling unless asked.
42	8. Produce the codebase map: Write a structured summary to the top of `AUDIT.md`:
43	- Stack summary (language, framework, runtime)
44	- File count by category
45	- Module/directory architecture
46	- Entry points
47	- High-coupling modules (most imports in + out)
48	- Linter output summary (if available)
49
50	Output of Pass 0: The "Codebase Overview" section of `AUDIT.md`. No findings yet.
51
52	### Pass 1 — Patterns & Consistency
53
54	Scan for mechanical quality issues that don't require deep semantic understanding. Process file-by-file, prioritizing high-coupling modules first (from Pass 0's dependency map).
55
56	What to scan (load `~/.claude/skills/deslop/references/checklist.md` categories 8-14):
57	- Naming convention violations and inconsistencies
58	- DRY violations — duplicated logic blocks, copy-pasted code
59	- Dead code — unused functions, unreachable branches, commented-out code, unused imports
60	- Magic numbers and hardcoded values
61	- Missing type annotations (for typed languages)
62	- Inconsistent patterns (e.g., callbacks in one file, promises in another)
63	- KISS/YAGNI violations — unnecessary abstractions, premature optimization
64	- Dependency issues — unused deps, circular imports
65
66	Chunking strategy for large files (>500 lines): Read in function/class-sized chunks. Never split in the middle of a function. When analyzing a chunk, re-read the file's import header for context.
67
68	For each finding: Write it to `AUDIT.md` using the format from `~/.claude/skills/deslop/references/audit-format.md`.
69
70	### Pass 2 — Logic & Resilience
71
72	Trace critical paths through the code. This pass requires cross-file context.
73
74	Start from entry points identified in Pass 0. For each critical path:
75	1. Trace the happy path from input to output.
76	2. Then ask: what happens when each step fails?
77	3. Check every error handling point: is the error caught? Logged? Re-thrown? Swallowed?
78	4. Check edge cases: null/undefined inputs, empty collections, boundary values, concurrent access.
79	5. Check data validation at trust boundaries (user input, API responses, file reads, env vars).
80
81	What to scan (load `~/.claude/skills/deslop/references/checklist.md` categories 2-4):
82	- Correctness bu

People who liked this also viewed

6 picks

Type