acreadiness-policy

Name: acreadiness-policy
Author: github

37kstars4.6kforks

How to install acreadiness-policy?

github/awesome-copilot/acreadiness-policy

$npx -y skills add github/awesome-copilot --skill acreadiness-policy

Installs into the current project.

Summary

Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scor

Files · 1

View on GitHub

SKILL.md

1	# /acreadiness-policy — AgentRC policies
2
3	Use this skill when the user asks about policies, strict mode, custom scoring, disabling checks, org standards, or CI gating of readiness.
4
5	A policy is a small JSON file with three optional sections — `criteria`, `extras`, `thresholds` — that customise how AgentRC scores readiness.
6
7	## Built-in examples
8
9	AgentRC ships with three example policies in `examples/policies/`:
10
11	\| Policy \| What it does \|
12	\|---\|---\|
13	\| `strict.json` \| 100% pass rate, raises impact on key criteria \|
14	\| `ai-only.json` \| Disables all repo-health checks, focuses on AI tooling \|
15	\| `repo-health-only.json` \| Disables AI checks, focuses on traditional quality \|
16
17	Recommend these as starting points before writing a custom policy.
18
19	## Policy schema
20
21	```jsonc
22	{
23	"name": "my-policy",
24	"criteria": {
25	"disable": ["env-example", "observability", "dependabot"],
26	"override": {
27	"readme": { "impact": "high", "level": 2 },
28	"lint-config": { "title": "Linter required" }
29	}
30	},
31	"extras": {
32	"disable": ["pre-commit"]
33	},
34	"thresholds": {
35	"passRate": 0.9
36	}
37	}
38	```
39
40	### Impact weights
41
42	\| Impact \| Weight \|
43	\|---\|---\|
44	\| critical \| 5 \|
45	\| high \| 4 \|
46	\| medium \| 3 \|
47	\| low \| 2 \|
48	\| info \| 0 \|
49
50	`Score = 1 − (deductions / max possible weight)`. Grades: A ≥ 0.9, B ≥ 0.8, C ≥ 0.7, D ≥ 0.6, F < 0.6.
51
52	## Sub-commands
53
54	### `show`
55	List policies currently in effect (from `agentrc.config.json` `policies` array, or none).
56
57	### `new <name>`
58	Scaffold `policies/<name>.json` with sensible defaults. Walk the user through:
59	1. What to disable — irrelevant pillars or extras for their stack (e.g. disable `observability` for a static site).
60	2. What to raise — override `impact` to `high` or `critical` for must-haves (e.g. `readme`, `codeowners`).
61	3. Pass-rate threshold — typical org baselines: `0.7` (lenient), `0.85` (standard), `1.0` (strict).
62	4. Reference the policy from `agentrc.config.json`:
63	```json
64	{ "policies": ["./policies/<name>.json"] }
65	```
66
67	### `apply <path-or-pkg>`
68	Run `agentrc readiness --json --policy <source>` and re-render the report by handing off to the `assess` skill / `ai-readiness-reporter` agent. Supports chaining:
69	```bash
70	npx -y github:microsoft/agentrc readiness --json --policy ./org-baseline.json,./team-frontend.json
71	```
72
73	## CI gating
74
75	Combine policies with `--fail-level` to enforce a minimum maturity level in CI:
76
77	```yaml
78	- run: npx -y github:microsoft/agentrc readiness --policy ./policies/strict.json --fail-level 3
79	```
80
81	## Advanced
82
83	JSON policies can disable, override, and set thresholds — but cannot add new criteria. For new detection logic, point users at AgentRC's TypeScript plugin system (`docs/dev/plugins.md`).
84
85	## Operating rules
86
87	- Never silently disable a pillar. If the user wants to disable `observability`, confirm and explain the trade-off.
88	- Prefer overriding `impact` over disabling. Disabling hides the gap entirely; overriding lets it still appear in the report.
89	- Recommend extras stay enabled. They cost nothing — they don't affect the score.
90	- Suggest layering — most orgs want a baseline policy + per-team overrides chained with `--policy a.json,b.json`.

People who liked this also viewed

6 picks

Type

acreadiness-policy

37kstars4.6kforks

View on GitHub

How to install acreadiness-policy?

github/awesome-copilot/acreadiness-policy

$npx -y skills add github/awesome-copilot --skill acreadiness-policy

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# /acreadiness-policy — AgentRC policies
2
3	Use this skill when the user asks about policies, strict mode, custom scoring, disabling checks, org standards, or CI gating of readiness.
4
5	A policy is a small JSON file with three optional sections — `criteria`, `extras`, `thresholds` — that customise how AgentRC scores readiness.
6
7	## Built-in examples
8
9	AgentRC ships with three example policies in `examples/policies/`:
10
11	\| Policy \| What it does \|
12	\|---\|---\|
13	\| `strict.json` \| 100% pass rate, raises impact on key criteria \|
14	\| `ai-only.json` \| Disables all repo-health checks, focuses on AI tooling \|
15	\| `repo-health-only.json` \| Disables AI checks, focuses on traditional quality \|
16
17	Recommend these as starting points before writing a custom policy.
18
19	## Policy schema
20
21	```jsonc
22	{
23	"name": "my-policy",
24	"criteria": {
25	"disable": ["env-example", "observability", "dependabot"],
26	"override": {
27	"readme": { "impact": "high", "level": 2 },
28	"lint-config": { "title": "Linter required" }
29	}
30	},
31	"extras": {
32	"disable": ["pre-commit"]
33	},
34	"thresholds": {
35	"passRate": 0.9
36	}
37	}
38	```
39
40	### Impact weights
41
42	\| Impact \| Weight \|
43	\|---\|---\|
44	\| critical \| 5 \|
45	\| high \| 4 \|
46	\| medium \| 3 \|
47	\| low \| 2 \|
48	\| info \| 0 \|
49
50	`Score = 1 − (deductions / max possible weight)`. Grades: A ≥ 0.9, B ≥ 0.8, C ≥ 0.7, D ≥ 0.6, F < 0.6.
51
52	## Sub-commands
53
54	### `show`
55	List policies currently in effect (from `agentrc.config.json` `policies` array, or none).
56
57	### `new <name>`
58	Scaffold `policies/<name>.json` with sensible defaults. Walk the user through:
59	1. What to disable — irrelevant pillars or extras for their stack (e.g. disable `observability` for a static site).
60	2. What to raise — override `impact` to `high` or `critical` for must-haves (e.g. `readme`, `codeowners`).
61	3. Pass-rate threshold — typical org baselines: `0.7` (lenient), `0.85` (standard), `1.0` (strict).
62	4. Reference the policy from `agentrc.config.json`:
63	```json
64	{ "policies": ["./policies/<name>.json"] }
65	```
66
67	### `apply <path-or-pkg>`
68	Run `agentrc readiness --json --policy <source>` and re-render the report by handing off to the `assess` skill / `ai-readiness-reporter` agent. Supports chaining:
69	```bash
70	npx -y github:microsoft/agentrc readiness --json --policy ./org-baseline.json,./team-frontend.json
71	```
72
73	## CI gating
74
75	Combine policies with `--fail-level` to enforce a minimum maturity level in CI:
76
77	```yaml
78	- run: npx -y github:microsoft/agentrc readiness --policy ./policies/strict.json --fail-level 3
79	```
80
81	## Advanced
82
83	JSON policies can disable, override, and set thresholds — but cannot add new criteria. For new detection logic, point users at AgentRC's TypeScript plugin system (`docs/dev/plugins.md`).
84
85	## Operating rules
86
87	- Never silently disable a pillar. If the user wants to disable `observability`, confirm and explain the trade-off.
88	- Prefer overriding `impact` over disabling. Disabling hides the gap entirely; overriding lets it still appear in the report.
89	- Recommend extras stay enabled. They cost nothing — they don't affect the score.
90	- Suggest layering — most orgs want a baseline policy + per-team overrides chained with `--policy a.json,b.json`.

People who liked this also viewed

6 picks

Type