Skip to content

Commit de24ed0

Browse files
durandomclaude
durandom
and
claude
committed
feat: add help subcommand to /fullsend skill
Context-aware onboarding companion that shows the agent pipeline, inspects the local .fullsend/ deployment, and links to upstream docs. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1 parent 1136d43 commit de24ed0

2 files changed

Lines changed: 203 additions & 0 deletions

File tree

‎.claude/skills/fullsend/SKILL.md‎

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -11,6 +11,9 @@ description: |
1111
watch or monitor a fullsend run, comment on an issue, or manage labels.
1212
Also use when asked to run sandbox diagnostics, debug the sandbox environment,
1313
check if yarn/corepack/openspec work, or build a custom fullsend agent.
14+
Also use when asked what fullsend agents are, how they work, how to use them,
15+
what agents are available, how to get started with fullsend, or how the local
16+
deployment is configured.
1417
---
1518

1619
# /fullsend
@@ -91,6 +94,7 @@ To add a variable, create an env file and wire it via `host_files` in the harnes
9194
| `debug <#issue> [--repo]` | Run sandbox diagnostics (shortcut for `trigger debug`) |
9295
| `comment <#issue> <message> [--repo]` | Post a comment on an issue or PR |
9396
| `label <#issue> <add\|remove> <label> [--repo]` | Add or remove a label on an issue or PR |
97+
| `help [topic]` | Onboarding companion — agent pipeline, local deployment overview, upstream docs |
9498

9599
If no arguments are given, display this table and ask which the user wants.
96100

@@ -111,6 +115,7 @@ Parse the first word after `/fullsend` as the subcommand.
111115
| `debug` | `references/debug.md` |
112116
| `comment` | `references/comment.md` |
113117
| `label` | `references/label.md` |
118+
| `help` | `references/help.md` |
114119

115120
</routing>
116121

‎.claude/skills/fullsend/references/help.md‎

Lines changed: 198 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,198 @@
1+
# help
2+
3+
Context-aware onboarding companion for fullsend. Shows the agent pipeline, inspects the local deployment's customizations, and links to upstream docs.
4+
5+
## Usage
6+
7+
```
8+
/fullsend help [topic]
9+
```
10+
11+
- No argument: show all sections
12+
- `agents`: agent pipeline and catalog
13+
- `setup` or `local`: getting started / running locally
14+
- `customization` or `config`: how to customize agents, skills, harness
15+
16+
## Procedure
17+
18+
### 1. Resolve the target repo
19+
20+
Follow the repo resolution order from the SKILL.md `<repo_resolution>` section to find the repo with `.fullsend/` configuration.
21+
22+
If in a monorepo (e.g., `rhdh-plugins`), note this — the agent operates at repo level, not workspace level.
23+
24+
### 2. Route by topic
25+
26+
| Argument | Sections to show |
27+
|----------|-----------------|
28+
| _(none)_ | All: pipeline → local deployment → upstream links |
29+
| `agents` | Pipeline + agent catalog only |
30+
| `setup` / `local` | Getting started links + prerequisites only |
31+
| `customization` / `config` | Local deployment inspection + customization links |
32+
33+
### 3. Agent pipeline (topic: `agents` or all)
34+
35+
Display this pipeline diagram:
36+
37+
```
38+
┌─────────────────── Fullsend Agent Pipeline ───────────────────┐
39+
│ │
40+
│ issue opened │
41+
│ │ │
42+
│ ▼ │
43+
│ triage ─── /fs-triage │
44+
│ │ │
45+
│ │ adds `ready-to-code` label (auto for bugs/docs/perf) │
46+
│ ▼ │
47+
│ code ──── /fs-code │
48+
│ │ │
49+
│ │ pushes branch, creates PR, adds `ready-for-review` │
50+
│ ▼ │
51+
│ review ─── /fs-review │
52+
│ │ │
53+
│ ├── approved ──────────────────────▶ merge │
54+
│ │ │ │
55+
│ └── changes requested ▼ │
56+
│ │ retro ── /fs-retro │
57+
│ ▼ │
58+
│ fix ──── /fs-fix │
59+
│ │ │
60+
│ └── back to review (max iterations capped) │
61+
│ │
62+
│ Scoring (independent): prioritize ── /fs-prioritize │
63+
│ Diagnostics: debug ──────── /fs-debug │
64+
│ │
65+
└───────────────────────────────────────────────────────────────┘
66+
```
67+
68+
Then show the agent catalog:
69+
70+
| Agent | Trigger | What it does |
71+
|-------|---------|-------------|
72+
| **triage** | New issue opened, `/fs-triage` | Assesses issue, asks clarifying questions, labels `ready-to-code` for bugs/docs/perf |
73+
| **code** | `ready-to-code` label, `/fs-code` | Implements fix/feature in sandbox, commits to feature branch |
74+
| **review** | `ready-for-review` label, `/fs-review` | Multi-dimension code review (correctness, security, style, docs) |
75+
| **fix** | Review requests changes, `/fs-fix` | Addresses specific review findings, pushes fix commit |
76+
| **retro** | PR merged/closed, `/fs-retro` | Retrospective on the full workflow — files improvement issues |
77+
| **prioritize** | Schedule or `/fs-prioritize` | RICE scoring for project board ranking |
78+
| **debug** | `/fs-debug` | Sandbox diagnostics — checks toolchain, network, env |
79+
80+
All agents run in a sandboxed container (OpenShell) with no direct push access. Pre/post scripts on the runner handle git operations and safety gates (secret scanning, protected path checks).
81+
82+
### 4. Local deployment inspection (topic: `customization` or all)
83+
84+
Read the target repo's `.fullsend/` directory and present a deployment summary. This section is dynamic — it reflects the actual state of the repo's configuration.
85+
86+
#### 4a. Read config.yaml
87+
88+
```bash
89+
cat <repo>/.fullsend/config.yaml
90+
```
91+
92+
Show which roles are enabled:
93+
```
94+
Enabled roles: triage, coder, review, fix
95+
```
96+
97+
#### 4b. Scan customized directory
98+
99+
```bash
100+
ls <repo>/.fullsend/customized/harness/*.yaml 2>/dev/null
101+
ls <repo>/.fullsend/customized/agents/*.md 2>/dev/null
102+
ls <repo>/.fullsend/customized/skills/*/SKILL.md 2>/dev/null
103+
ls <repo>/.fullsend/customized/env/*.env 2>/dev/null
104+
ls <repo>/.fullsend/customized/policies/*.yaml 2>/dev/null
105+
```
106+
107+
#### 4c. For each customized harness, read it and summarize the overrides
108+
109+
For each `*.yaml` in `customized/harness/`, read the file and extract:
110+
- `image` — what custom image is used (and why it differs from upstream)
111+
- `skills` — what skills are loaded (especially custom ones)
112+
- `host_files` — what extra env/config files are mounted
113+
- `policy` — which network policy is applied
114+
- `timeout_minutes` — if different from upstream default
115+
116+
Present as a per-agent summary:
117+
118+
```
119+
## Your Deployment
120+
121+
### code agent (customized)
122+
Image: ghcr.io/redhat-developer/rhdh-fullsend-code:latest
123+
Skills: code-implementation, monorepo-workspace-routing (custom)
124+
Env: gcp-vertex.env, code-agent.env, rhdh-toolchain.env (custom), yarn-proxy.env (custom)
125+
Policy: policies/code.yaml (custom — adds repo.yarnpkg.com, corepack binary)
126+
Timeout: 35 min
127+
Prompt: agents/code.md (customized — adds monorepo routing, zero-trust principle)
128+
129+
### fix agent (customized)
130+
Image: ghcr.io/redhat-developer/rhdh-fullsend-code:latest
131+
Skills: fix-review, monorepo-workspace-routing (custom)
132+
...
133+
134+
### triage agent (upstream defaults)
135+
### review agent (upstream defaults)
136+
```
137+
138+
Mark items as "(custom)" when they exist in `customized/` and differ from the upstream scaffold default. For agents without customizations, show as "upstream defaults."
139+
140+
#### 4d. Custom skills
141+
142+
For each skill in `customized/skills/`, read the `SKILL.md` and show name + description:
143+
144+
```
145+
### Custom Skills
146+
- monorepo-workspace-routing — Navigate to the correct workspace in a monorepo before starting work
147+
```
148+
149+
#### 4e. Custom env files
150+
151+
For each `.env` in `customized/env/`, show what it sets:
152+
153+
```
154+
### Custom Env Files
155+
- rhdh-toolchain.env — sets COREPACK_HOME=/tmp/corepack (writable dir for corepack)
156+
- yarn-proxy.env — maps HTTP_PROXY → YARN_HTTP_PROXY (yarn ignores standard proxy vars)
157+
```
158+
159+
### 5. Upstream docs (topic: `setup` or all)
160+
161+
Present as a linked reference table. Construct URLs as `https://github.com/fullsend-ai/fullsend/blob/main/<path>`.
162+
163+
```
164+
## Learn More
165+
166+
### Getting Started
167+
- [Installation & setup](https://github.com/fullsend-ai/fullsend/blob/main/docs/guides/getting-started/installation.md)
168+
- [GitHub setup](https://github.com/fullsend-ai/fullsend/blob/main/docs/guides/getting-started/github-setup.md)
169+
- [Running agents locally](https://github.com/fullsend-ai/fullsend/blob/main/docs/guides/user/running-agents-locally.md)
170+
171+
### Agent Reference
172+
- [Agent catalog](https://github.com/fullsend-ai/fullsend/blob/main/docs/agents/README.md)
173+
- [Code agent](https://github.com/fullsend-ai/fullsend/blob/main/docs/agents/code.md)
174+
- [Triage agent](https://github.com/fullsend-ai/fullsend/blob/main/docs/agents/triage.md)
175+
- [Review agent](https://github.com/fullsend-ai/fullsend/blob/main/docs/agents/review.md)
176+
- [Fix agent](https://github.com/fullsend-ai/fullsend/blob/main/docs/agents/fix.md)
177+
- [Prioritize agent](https://github.com/fullsend-ai/fullsend/blob/main/docs/agents/prioritize.md)
178+
- [Retro agent](https://github.com/fullsend-ai/fullsend/blob/main/docs/agents/retro.md)
179+
180+
### Customization
181+
- [Customizing agents (harness config)](https://github.com/fullsend-ai/fullsend/blob/main/docs/guides/user/customizing-agents.md)
182+
- [Customizing with AGENTS.md](https://github.com/fullsend-ai/fullsend/blob/main/docs/guides/user/customizing-with-agents-md.md)
183+
- [Customizing with skills](https://github.com/fullsend-ai/fullsend/blob/main/docs/guides/user/customizing-with-skills.md)
184+
- [Bugfix workflow](https://github.com/fullsend-ai/fullsend/blob/main/docs/guides/user/bugfix-workflow.md)
185+
186+
### Architecture
187+
- [Architecture overview](https://github.com/fullsend-ai/fullsend/blob/main/docs/architecture.md)
188+
- [Glossary](https://github.com/fullsend-ai/fullsend/blob/main/docs/glossary.md)
189+
- [Vision](https://github.com/fullsend-ai/fullsend/blob/main/docs/vision.md)
190+
```
191+
192+
### 6. Suggest next steps
193+
194+
Based on the context, suggest relevant `/fullsend` commands:
195+
196+
- "Run `/fullsend validate` to check your customizations against upstream for drift."
197+
- "Run `/fullsend trigger code #<N>` to trigger the code agent on an issue."
198+
- "Run `/fullsend inspect <run-id>` to investigate a specific agent run."

0 commit comments

Comments
 (0)