Skip to content
Agentmart
Submit a tool

chatcrystal-task-writeback

Write reusable ChatCrystal task memories after substantive work completes.

Skill by ZengLiangYi

IndexedApache-2.0★ 61
Write a review

Chalk Labs

Need help deploying chatcrystal-task-writeback?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/zengliangyi-chatcrystal-task-writeback

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through `write_task_memory` or emit a structured memory candidate for later save.

Use cases: writing, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/chatcrystal-task-writeback

What's inside

Skill name
chatcrystal-task-writeback
Description
Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through `write_task_memory` or emit a structured memory candidate for later save.
License
Apache-2.0
Instructions
109 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# ChatCrystal Task Writeback

Use this skill after meaningful work completes. Let ChatCrystal Core decide whether a memory should be skipped, merged, or created.

## Workflow

1. Trigger only after substantive work completes and the result produced reusable knowledge.
2. Good candidates include:
   - a durable fix
   - a meaningful pitfall
   - a reusable pattern
   - an explicit engineering decision

## Quality Gate Preflight

Before calling `write_task_memory`, verify the candidate is an experience asset, not a work log.

Do not call `write_task_memory` when:

- The summary only says what changed, without why it mattered.
- There is no clear problem, decision, pitfall, resolution, or reusable pattern.
- The task produced no durable lesson for future work.

Required field shape by `memory.outcome_type`:

- `fix`: include `root_cause` or `resolution`.
- `pitfall`: include `pitfalls` plus `resolution` or `reusable_patterns`.
- `decision`: include `decisions`.
- `pattern`: include `reusable_patterns`.

Write `memory.summary` as a durable experience conclusion, not as "I did X".
Automatic writeback must include `source_run_key`; without it, emit a structured candidate for later save instead of silently writing manual memory.

3. If `write_task_memory` is available and the runtime has a stable run or session key, call it with:
   - `mode: "auto"`
   - `source_run_key`: the stable run or session key
   - `task.goal`, `task.task_kind`, `task.project_dir`, `task.cwd`, `task.branch`
   - `task.source_agent` when known
   - `memory.summary`: concise and durable, not chatty
   - `memory.outcome_type`: one of `pitfall`, `fix`, `pattern`, `decision`
   - `memory.root_cause`, `memory.resolution`, `memory.error_signatures`, `memory.files_touched`, `memory.tags` when relevant
4. Use `mode: "manual"` only for an explicit manual save flow, never as a silent fallback for automatic writeback.
5. Default to project-scoped knowledge. Only use global scope for clearly cross-project knowledge and only in an explicit manual save flow.
6. Report the persistence result accurately:
   - `created`
   - `merged`
   - `skipped`

## Example MCP Input

Use this shape when calling `write_task_memory` after a completed task with a stable run key:

```json
{
  "mode": "auto",
  "source_run_key": "agent-session-or-run-id",
  "scope": "project",
  "task": {
    "goal": "Fix MCP recall schema validation",
    "task_kind": "debug",
    "project_dir": "/path/to/project",
    "cwd": "/path/to/project",
    "branch": "fix/mcp-recall-schema",
    "files_touched": [
      "server/src/services/memory/schemas.ts",
      "server/src/cli/mcp/server.ts"
    ],
    "error_signatures": [
      "invalid_type",
      "recall_for_task schema mismatch"
    ],
    "source_agent": "codex"
  },
  "memory": {
    "summary": "MCP tool schemas must stay aligned with memory service request shapes; mismatches surface as validation failures before tool execution.",
    "outcome_type": "fix",
    "root_cause": "The MCP tool input shape diverged from the service schema.",
    "resolution": "Reused the shared request shape in the MCP server registration.",
    "files_touched": [
      "server/src/services/memory/schemas.ts",
      "server/src/cli/mcp/server.ts"
    ],
    "tags": [
      "mcp",
      "memory-loop",
      "schema"
    ]
  }
}
```

## Full Mode

Full mode requires ChatCrystal Core plus MCP access to `write_task_memory`.

- Do not reimplement skip or merge logic in the skill.
- Trust Core to decide whether the memory should be skipped, merged, or created.
- If the tool reports `skipped`, keep the task result but do not force persistence.

## Degraded Mode

If ChatCrystal Core or the MCP tool is unavailable, or if no stable run key exists for automatic writeback:

- Do not claim that the memory was saved.
- Emit a structured memory candidate in the response for later save.
- Keep the candidate aligned with the `write_task_memory.memory` payload shape so it can be reused later.
- Do not instruct the runtime to auto-install ChatCrystal Core as part of the skill flow.

From ZengLiangYi/ChatCrystal, Apache-2.0.

Signals

Stars
61
Forks
5
Open issues
0
Contributors
2
Last commit (this folder)
Apr 29, 2026 (6 months ago)
Last release
Sep 20, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ZengLiangYi

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get chatcrystal-task-writeback running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying chatcrystal-task-writeback?

CallGet help
Cite this page

chatcrystal-task-writeback skill. Agent Mart. https://agentmart.dev/skills/zengliangyi-chatcrystal-task-writeback (last updated 2026-10-24)