academic-experiments

Name: academic-experiments
Author: joshua-zyy

101stars1forks

How to install academic-experiments?

joshua-zyy/academic-paper-writer/academic-experiments

$npx -y skills add joshua-zyy/academic-paper-writer --skill academic-experiments

Installs into the current project.

Summary

Audit, run, or verify experimental evidence for CS/AI/ML papers. Produces Evidence Inventory with evidence_type annotations (newly_run/preexisting_artifact/user_claim) and Protocol Risk assessments. Use when: checking if experiment results are reproducible, auditing existing expe

Files · 1

View on GitHub

SKILL.md

1	# Academic Experiments
2
3	将此 skill 视为"实验取证代理"，目标是建立最短且可信的证据链，而不是尽量多跑实验。
4
5	## Router Protocol
6
7	1. Read `manifest.yaml`. It declares `always_load` files, `axes`, and `references.on_demand`.
8	2. Read every file listed under `always_load`. These are the skill's binding rules — not reference material.
9	3. Apply the loaded material as constraints:
10	- `stance.md` defines non-negotiable rules, evidence type semantics, failure degradation, and scope.
11	- `red-lines.md` defines absolute prohibitions. Do not negotiate these.
12	- `output-contract.md` defines deliverables per mode and claim-readiness classification.
13	- `anti-patterns.md` defines known failure modes and their correct alternatives.
14	4. Detect the mode using the manifest's `mode` axis: `experiment-evidence-pass`, `evidence-inventory-only`, or `minimal-reproducible-run`. Align evidence type semantics to `../shared/core/evidence-policy.md`.
15	5. Echo the selected mode to the user before executing.
16	6. Reach for `references/` only when the manifest's `references.on_demand` condition is satisfied.
17
18	## Modes
19
20	\| Mode \| Use when \|
21	\|---\|---\|
22	\| `experiment-evidence-pass` \| Full audit: inventory + run + record + risk analysis \|
23	\| `evidence-inventory-only` \| Inventory existing artifacts only, no execution \|
24	\| `minimal-reproducible-run` \| Execute minimal reproducible command (e.g. eval existing checkpoint) \|
25
26	## Agent Dispatch
27
28	`agents/experiment_agent.md` is dispatched by `academic-paper-writer` orchestrator at Step 4. The agent may run experiments but must not modify project source code or data files, nor write paper prose independently.
29
30	## Independent Use
31
32	\| Input \| Mode \| Priority \| Behavior \|
33	\|---\|---\|---\|---\|
34	\| `repo_path` + no run mode \| experiment-evidence-pass \| 2 (path trigger) \| Full audit: inventory → env → minimal run → risk \|
35	\| `repo_path` + "inspect only" \| evidence-inventory-only \| 1 (explicit) \| Inventory only, no commands \|
36	\| `repo_path` + specific command \| minimal-reproducible-run \| 1 (explicit) \| Verify env → execute → record \|
37	\| No `repo_path` \| — \| 3 (no input) \| Ask path, or auto-detect entry files \|
38
39	\| Scenario \| Recommended \|
40	\|---\|---\|
41	\| Just auditing/reproducing evidence \| This skill (standalone) \|
42	\| Writing results into paper prose \| academic-paper-writer orchestrator \|
43	\| Draft results need verification \| This skill → academic-reviser \|

People who liked this also viewed

6 picks

Type

academic-experiments

101stars1forks

View on GitHub

How to install academic-experiments?

joshua-zyy/academic-paper-writer/academic-experiments

$npx -y skills add joshua-zyy/academic-paper-writer --skill academic-experiments

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Academic Experiments
2
3	将此 skill 视为"实验取证代理"，目标是建立最短且可信的证据链，而不是尽量多跑实验。
4
5	## Router Protocol
6
7	1. Read `manifest.yaml`. It declares `always_load` files, `axes`, and `references.on_demand`.
8	2. Read every file listed under `always_load`. These are the skill's binding rules — not reference material.
9	3. Apply the loaded material as constraints:
10	- `stance.md` defines non-negotiable rules, evidence type semantics, failure degradation, and scope.
11	- `red-lines.md` defines absolute prohibitions. Do not negotiate these.
12	- `output-contract.md` defines deliverables per mode and claim-readiness classification.
13	- `anti-patterns.md` defines known failure modes and their correct alternatives.
14	4. Detect the mode using the manifest's `mode` axis: `experiment-evidence-pass`, `evidence-inventory-only`, or `minimal-reproducible-run`. Align evidence type semantics to `../shared/core/evidence-policy.md`.
15	5. Echo the selected mode to the user before executing.
16	6. Reach for `references/` only when the manifest's `references.on_demand` condition is satisfied.
17
18	## Modes
19
20	\| Mode \| Use when \|
21	\|---\|---\|
22	\| `experiment-evidence-pass` \| Full audit: inventory + run + record + risk analysis \|
23	\| `evidence-inventory-only` \| Inventory existing artifacts only, no execution \|
24	\| `minimal-reproducible-run` \| Execute minimal reproducible command (e.g. eval existing checkpoint) \|
25
26	## Agent Dispatch
27
28	`agents/experiment_agent.md` is dispatched by `academic-paper-writer` orchestrator at Step 4. The agent may run experiments but must not modify project source code or data files, nor write paper prose independently.
29
30	## Independent Use
31
32	\| Input \| Mode \| Priority \| Behavior \|
33	\|---\|---\|---\|---\|
34	\| `repo_path` + no run mode \| experiment-evidence-pass \| 2 (path trigger) \| Full audit: inventory → env → minimal run → risk \|
35	\| `repo_path` + "inspect only" \| evidence-inventory-only \| 1 (explicit) \| Inventory only, no commands \|
36	\| `repo_path` + specific command \| minimal-reproducible-run \| 1 (explicit) \| Verify env → execute → record \|
37	\| No `repo_path` \| — \| 3 (no input) \| Ask path, or auto-detect entry files \|
38
39	\| Scenario \| Recommended \|
40	\|---\|---\|
41	\| Just auditing/reproducing evidence \| This skill (standalone) \|
42	\| Writing results into paper prose \| academic-paper-writer orchestrator \|
43	\| Draft results need verification \| This skill → academic-reviser \|

People who liked this also viewed

6 picks

Type