skill-align

Name: skill-align
Author: techygarg

165stars12forks

How to install skill-align?

techygarg/lattice/skill-align

$npx -y skills add techygarg/lattice --skill skill-align

Installs into the current project.

Summary

Audit and fix all Lattice documentation, README, docs/, PROJECT.md, GitHub issue templates, and CLAUDE.md to ensure they are fully aligned with the current skill inventory. Documentation drift is the most common source of user confusion in Lattice — a skill exists in the codebase

Files · 1

View on GitHub

SKILL.md

1	# Lattice Sync
2
3	Core responsibility: Keep every public-facing document in sync with the actual skill inventory. The skills directory is the source of truth — all documents derive from it.
4
5	Input: None required. Reads the live state of `skills/` and all documentation on every run. Optionally: a specific skill name or tier to focus the audit.
6
7	Output:
8	- A findings report listing every gap as `[GAP]`, `[STALE]`, or `[WRONG]` with file and description
9	- All found gaps fixed in-place across: `README.md`, `docs/how-it-works.md`, `docs/configuration.md`, `docs/practical-guide.md`, `PROJECT.md`, `CLAUDE.md`, `.github/ISSUE_TEMPLATE/bug_report.yml`
10	- A final clean confirmation: "No gaps found" or a list of what was changed
11
12	How to verify this skill did its job:
13	```bash
14	grep -rn "requirements atom\\|framework:requirements\b" \
15	docs/ README.md PROJECT.md CLAUDE.md .github/ skills/ \
16	--include=".md" --include=".yml"
17	```
18	Any result from this grep means the sync is incomplete. A clean run returns no output.
19
20	Also verify: every skill in `skills/` appears in the bug_report.yml dropdown and the how-it-works.md inventory tables.
21
22	## When to run
23
24	- After creating any new atom, molecule, or refiner
25	- After renaming or removing a skill
26	- After changing a skill's config key, consumed-by relationships, or output path
27	- When a user suspects docs are out of date
28
29	## Phase 1 — Build the live inventory
30
31	Read the skills directory tree. STOP: do NOT assume you already know the inventory — always read from files.
32
33	```bash
34	find skills/ -name "SKILL.md" \| sort
35	```
36
37	For each SKILL.md found, extract:
38	- `name:` field (frontmatter)
39	- `tier:` inferred from path (`atoms/`, `molecules/`, `refiners/`)
40	- Config key: grep for `paths\.\w+` in the file
41	- Consumes: grep for `framework:` references (molecules only)
42	- Produces: grep for `.lattice/standards/` path (refiners only)
43	- Output subfolder: grep for `.lattice/\w+/` paths (molecules only)
44
45	Build a structured inventory:
46	```
47	atoms: [name, config_key, has_refiner, has_defaults_md]
48	molecules: [name, composes[], output_subfolder]
49	refiners: [name, config_key, produces_path, consumed_by_atom]
50	```
51
52	Read `references/audit-checklist.md` for the complete per-document audit rules before starting Phase 2.
53
54	---
55
56	## Phase 2 — Audit each document
57
58	Work through every document in this order. For each, apply the checks in `references/audit-checklist.md`. STOP: a document with zero findings gets no entry in the report — do not print a heading or a "no gaps" line for it. Log every finding as:
59
60	```
61	[GAP] file:line — description of what is missing or wrong
62	[STALE] file:line — description of what refers to something that no longer exists
63	[WRONG] file:line — description of a relationship (consumed-by, produces) that is incorrect
64	```
65
66	Documents to audit:
67	1. `docs/how-it-works.md`
68	2. `docs/configuration.md`
69	3. `docs/practical-guide.md`
70	4. `README.md`
71	5. `PROJECT.md` — Skill Conventions, Known subfolders list, and Repository Structure counts all live here
72	6. `.github/ISSUE_TEMPLATE/bug_report.yml`
73	7. `.github/ISSUE_TEMPLATE/skill_request.yml` (generic — only check if skill-specific examples are present)
74	8. `.github/ISSUE_TEMPLATE/documentation.yml` (generic — only check if skill names appear)
75	9. `knowledge-base/requirement-forge-requirements.md` (if exists — check it matches current skill names)
76
77	Present a consolidated findings report before making any changes:
78
79	```
80	## Lattice Sync — Findings
81
82	### docs/how-it-works.md
83	[GAP] Atoms table missing: requirement-quality
84	[STALE] Refiners in Depth: requirement-forge-refiner consumed-by says "molecule" but should say "requirement-quality atom"
85
86	### .github/ISSUE_TEMPLATE/bug_report.yml
87	[GAP] Skill dropdown missing: requirement-quality (atom)
88
89	Total: N gaps, M stale references, P wrong relationships
90	```
91
92	Ask: "Ready to apply all fixes? Or are there any findings you want to skip?"
93
94	---
95
96	## Phase 3 — Fix
97
98	Apply every agreed fix. For each document, make all changes in a single edit pass. STOP: do not make multiple passes over the same file.
99
100	After all fixes are applied, run one final verification grep to confirm no old references remain:
101
102	```bash
103	# Check for stale atom names or wrong consumed-by text
104	gr

People who liked this also viewed

6 picks

Type

skill-align

165stars12forks

View on GitHub

How to install skill-align?

techygarg/lattice/skill-align

$npx -y skills add techygarg/lattice --skill skill-align

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Lattice Sync
2
3	Core responsibility: Keep every public-facing document in sync with the actual skill inventory. The skills directory is the source of truth — all documents derive from it.
4
5	Input: None required. Reads the live state of `skills/` and all documentation on every run. Optionally: a specific skill name or tier to focus the audit.
6
7	Output:
8	- A findings report listing every gap as `[GAP]`, `[STALE]`, or `[WRONG]` with file and description
9	- All found gaps fixed in-place across: `README.md`, `docs/how-it-works.md`, `docs/configuration.md`, `docs/practical-guide.md`, `PROJECT.md`, `CLAUDE.md`, `.github/ISSUE_TEMPLATE/bug_report.yml`
10	- A final clean confirmation: "No gaps found" or a list of what was changed
11
12	How to verify this skill did its job:
13	```bash
14	grep -rn "requirements atom\\|framework:requirements\b" \
15	docs/ README.md PROJECT.md CLAUDE.md .github/ skills/ \
16	--include=".md" --include=".yml"
17	```
18	Any result from this grep means the sync is incomplete. A clean run returns no output.
19
20	Also verify: every skill in `skills/` appears in the bug_report.yml dropdown and the how-it-works.md inventory tables.
21
22	## When to run
23
24	- After creating any new atom, molecule, or refiner
25	- After renaming or removing a skill
26	- After changing a skill's config key, consumed-by relationships, or output path
27	- When a user suspects docs are out of date
28
29	## Phase 1 — Build the live inventory
30
31	Read the skills directory tree. STOP: do NOT assume you already know the inventory — always read from files.
32
33	```bash
34	find skills/ -name "SKILL.md" \| sort
35	```
36
37	For each SKILL.md found, extract:
38	- `name:` field (frontmatter)
39	- `tier:` inferred from path (`atoms/`, `molecules/`, `refiners/`)
40	- Config key: grep for `paths\.\w+` in the file
41	- Consumes: grep for `framework:` references (molecules only)
42	- Produces: grep for `.lattice/standards/` path (refiners only)
43	- Output subfolder: grep for `.lattice/\w+/` paths (molecules only)
44
45	Build a structured inventory:
46	```
47	atoms: [name, config_key, has_refiner, has_defaults_md]
48	molecules: [name, composes[], output_subfolder]
49	refiners: [name, config_key, produces_path, consumed_by_atom]
50	```
51
52	Read `references/audit-checklist.md` for the complete per-document audit rules before starting Phase 2.
53
54	---
55
56	## Phase 2 — Audit each document
57
58	Work through every document in this order. For each, apply the checks in `references/audit-checklist.md`. STOP: a document with zero findings gets no entry in the report — do not print a heading or a "no gaps" line for it. Log every finding as:
59
60	```
61	[GAP] file:line — description of what is missing or wrong
62	[STALE] file:line — description of what refers to something that no longer exists
63	[WRONG] file:line — description of a relationship (consumed-by, produces) that is incorrect
64	```
65
66	Documents to audit:
67	1. `docs/how-it-works.md`
68	2. `docs/configuration.md`
69	3. `docs/practical-guide.md`
70	4. `README.md`
71	5. `PROJECT.md` — Skill Conventions, Known subfolders list, and Repository Structure counts all live here
72	6. `.github/ISSUE_TEMPLATE/bug_report.yml`
73	7. `.github/ISSUE_TEMPLATE/skill_request.yml` (generic — only check if skill-specific examples are present)
74	8. `.github/ISSUE_TEMPLATE/documentation.yml` (generic — only check if skill names appear)
75	9. `knowledge-base/requirement-forge-requirements.md` (if exists — check it matches current skill names)
76
77	Present a consolidated findings report before making any changes:
78
79	```
80	## Lattice Sync — Findings
81
82	### docs/how-it-works.md
83	[GAP] Atoms table missing: requirement-quality
84	[STALE] Refiners in Depth: requirement-forge-refiner consumed-by says "molecule" but should say "requirement-quality atom"
85
86	### .github/ISSUE_TEMPLATE/bug_report.yml
87	[GAP] Skill dropdown missing: requirement-quality (atom)
88
89	Total: N gaps, M stale references, P wrong relationships
90	```
91
92	Ask: "Ready to apply all fixes? Or are there any findings you want to skip?"
93
94	---
95
96	## Phase 3 — Fix
97
98	Apply every agreed fix. For each document, make all changes in a single edit pass. STOP: do not make multiple passes over the same file.
99
100	After all fixes are applied, run one final verification grep to confirm no old references remain:
101
102	```bash
103	# Check for stale atom names or wrong consumed-by text
104	gr

People who liked this also viewed

6 picks

Type