optimizing

Name: optimizing
Author: OdradekAI

290stars23forks

How to install optimizing?

odradekai/bundles-forge/optimizing

$npx -y skills add OdradekAI/bundles-forge --skill optimizing

Installs into the current project.

Summary

Use when optimizing a bundle-plugin or single skill — improving descriptions, reducing tokens, fixing audit findings, restructuring workflows, adding skills to fill gaps, or iterating on user feedback

Files · 1

View on GitHub

SKILL.md

1	# Optimizing Bundle-Plugins
2
3	## Overview
4
5	Orchestrate targeted improvement of a bundle-plugin project or a single skill. Unlike a full audit, optimization focuses on goals: better triggering, lower token cost, tighter workflow chains, and feedback-driven skill refinement. This skill diagnoses issues, decides on improvements, and delegates content changes to `bundles-forge:authoring`.
6
7	Core principle: Optimize for the agent's experience. Diagnose → decide → delegate → verify.
8
9	Skill type: Hybrid — follow the execution flow rigidly (diagnose → decide → delegate → verify), but select targets and adapt execution strategies flexibly based on audit findings and user goals.
10
11	Announce at start: "I'm using the optimizing skill to improve [this project / this skill]."
12
13	## Step 1: Resolve Input & Detect Scope
14
15	The target can be a local path, a GitHub URL, or a zip file. Normalize the input to a local directory before scope detection.
16
17	### Input Normalization
18
19	> Edge cases & naming conventions: `bundles-forge:auditing` — `references/input-normalization.md`
20
21	This is a mandatory step — do not skip it or improvise paths. Resolve the target to a local directory before proceeding to Scope Detection.
22
23	1. Resolve the workspace. The workspace is `$CLAUDE_PROJECT_DIR` or `$CURSOR_PROJECT_DIR` (plugin mode), falling back to the current working directory.
24	2. Normalize the target by type:
25	- Local path — use directly; no transformation needed.
26	- GitHub URL — parse `<owner>` and `<repo>` from the URL. Shallow-clone to `<workspace>/.bundles-forge/repos/<owner>__<repo>/` using `--depth 1 --no-checkout`, then run `git checkout`. If the directory already exists, append a `__<YYYYMMDD>` timestamp to avoid collisions. Do not clone to `/tmp/`, `~/`, or any path outside `.bundles-forge/repos/`.
27	- Zip/tar.gz — extract to `<workspace>/.bundles-forge/repos/<archive-name>/`.
28	3. Create the target subdirectory if it does not exist.
29	4. On failure (network error, 404, auth required, rate limit): tell the user what failed and suggest providing a local path or zip file instead. Do not silently skip or proceed with partial data.
30
31	See the canonical source for the full naming convention (version/timestamp suffixes), GitHub subdirectory URLs, and security rules.
32
33	### Scope Detection
34
35	Prerequisites: Target resolved to a local path (via Input Normalization above).
36
37	After normalization, determine the scope from the resolved local path:
38
39	\| Target \| How to Detect \| Mode \|
40	\|--------\|--------------\|------\|
41	\| Project root \| Has `skills/` directory and `package.json` \| Project optimization — all 6 targets \|
42	\| Single skill directory \| Contains `SKILL.md` but no `skills/` subdirectory \| Skill optimization — 3 targets + feedback iteration \|
43	\| Single SKILL.md file \| Path ends in `SKILL.md` \| Skill optimization — 3 targets + feedback iteration \|
44
45	If the target is a single skill, skip to the Skill Optimization section below.
46
47	---
48
49	## Project Optimization
50
51	### Process
52
53	1. Diagnose — run audit scripts, assess skill health, detect workflow gaps
54	2. Classify & Route — classify action type, select applicable targets
55	3. Apply — execute selected targets, delegate content changes to authoring
56	4. Verify — re-audit to confirm improvement
57
58	### Diagnostic Tools
59
60	#### Audit Script Baseline
61
62	Run the quality linter to identify frontmatter issues, description anti-patterns, and broken references before manual optimization:
63
64	```bash
65	bundles-forge audit-skill <target-dir> # markdown report
66	bundles-forge audit-skill --json <target-dir> # machine-readable
67	```
68
69	The linter automates checks Q1-Q15 and X1-X3 from the skill quality ruleset. Focus manual effort on the subjective targets below.
70
71	#### Skill Health Assessment
72
73	Assess each skill across four qualitative dimensions: trigger confidence, execution clarity, end-to-end completeness, and degradation signals. See `references/optimization-decision-trees.md` for the full assessment framework and signal-to-target mapping.
74
75	#### Workflow Gap Detection
76
77	When findings reveal structural gaps (not just broken connections but missing capabilities), consider creating new skills via the CAPTURED action type. See `references/optimization-decision-trees.md` for the gap detection signals.
78
79	### Routing & Classification
80
81	Route findings to targets and classify each action (FIX / DERIVED / CAPTURED) before delegating. See `references/optimization-decision-trees.md` for:
82	- Target routing table — map

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

optimizing

290stars23forks

View on GitHub

How to install optimizing?

odradekai/bundles-forge/optimizing

$npx -y skills add OdradekAI/bundles-forge --skill optimizing

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Optimizing Bundle-Plugins
2
3	## Overview
4
5	Orchestrate targeted improvement of a bundle-plugin project or a single skill. Unlike a full audit, optimization focuses on goals: better triggering, lower token cost, tighter workflow chains, and feedback-driven skill refinement. This skill diagnoses issues, decides on improvements, and delegates content changes to `bundles-forge:authoring`.
6
7	Core principle: Optimize for the agent's experience. Diagnose → decide → delegate → verify.
8
9	Skill type: Hybrid — follow the execution flow rigidly (diagnose → decide → delegate → verify), but select targets and adapt execution strategies flexibly based on audit findings and user goals.
10
11	Announce at start: "I'm using the optimizing skill to improve [this project / this skill]."
12
13	## Step 1: Resolve Input & Detect Scope
14
15	The target can be a local path, a GitHub URL, or a zip file. Normalize the input to a local directory before scope detection.
16
17	### Input Normalization
18
19	> Edge cases & naming conventions: `bundles-forge:auditing` — `references/input-normalization.md`
20
21	This is a mandatory step — do not skip it or improvise paths. Resolve the target to a local directory before proceeding to Scope Detection.
22
23	1. Resolve the workspace. The workspace is `$CLAUDE_PROJECT_DIR` or `$CURSOR_PROJECT_DIR` (plugin mode), falling back to the current working directory.
24	2. Normalize the target by type:
25	- Local path — use directly; no transformation needed.
26	- GitHub URL — parse `<owner>` and `<repo>` from the URL. Shallow-clone to `<workspace>/.bundles-forge/repos/<owner>__<repo>/` using `--depth 1 --no-checkout`, then run `git checkout`. If the directory already exists, append a `__<YYYYMMDD>` timestamp to avoid collisions. Do not clone to `/tmp/`, `~/`, or any path outside `.bundles-forge/repos/`.
27	- Zip/tar.gz — extract to `<workspace>/.bundles-forge/repos/<archive-name>/`.
28	3. Create the target subdirectory if it does not exist.
29	4. On failure (network error, 404, auth required, rate limit): tell the user what failed and suggest providing a local path or zip file instead. Do not silently skip or proceed with partial data.
30
31	See the canonical source for the full naming convention (version/timestamp suffixes), GitHub subdirectory URLs, and security rules.
32
33	### Scope Detection
34
35	Prerequisites: Target resolved to a local path (via Input Normalization above).
36
37	After normalization, determine the scope from the resolved local path:
38
39	\| Target \| How to Detect \| Mode \|
40	\|--------\|--------------\|------\|
41	\| Project root \| Has `skills/` directory and `package.json` \| Project optimization — all 6 targets \|
42	\| Single skill directory \| Contains `SKILL.md` but no `skills/` subdirectory \| Skill optimization — 3 targets + feedback iteration \|
43	\| Single SKILL.md file \| Path ends in `SKILL.md` \| Skill optimization — 3 targets + feedback iteration \|
44
45	If the target is a single skill, skip to the Skill Optimization section below.
46
47	---
48
49	## Project Optimization
50
51	### Process
52
53	1. Diagnose — run audit scripts, assess skill health, detect workflow gaps
54	2. Classify & Route — classify action type, select applicable targets
55	3. Apply — execute selected targets, delegate content changes to authoring
56	4. Verify — re-audit to confirm improvement
57
58	### Diagnostic Tools
59
60	#### Audit Script Baseline
61
62	Run the quality linter to identify frontmatter issues, description anti-patterns, and broken references before manual optimization:
63
64	```bash
65	bundles-forge audit-skill <target-dir> # markdown report
66	bundles-forge audit-skill --json <target-dir> # machine-readable
67	```
68
69	The linter automates checks Q1-Q15 and X1-X3 from the skill quality ruleset. Focus manual effort on the subjective targets below.
70
71	#### Skill Health Assessment
72
73	Assess each skill across four qualitative dimensions: trigger confidence, execution clarity, end-to-end completeness, and degradation signals. See `references/optimization-decision-trees.md` for the full assessment framework and signal-to-target mapping.
74
75	#### Workflow Gap Detection
76
77	When findings reveal structural gaps (not just broken connections but missing capabilities), consider creating new skills via the CAPTURED action type. See `references/optimization-decision-trees.md` for the gap detection signals.
78
79	### Routing & Classification
80
81	Route findings to targets and classify each action (FIX / DERIVED / CAPTURED) before delegating. See `references/optimization-decision-trees.md` for:
82	- Target routing table — map

People who liked this also viewed

6 picks

Type