CCS Task Delegation
kaitranntt/ccs
Hands simple, deterministic tasks such as typo fixes, tests and small refactors to cheaper models through the ccs CLI, choosing a profile from your config.
Entry point for local AI conversation history across Claude Code, Codex and Kimi CLI: routes each request to the reader or continuation skill that owns it and keeps the cross-provider inventory.
MITAuto-check passed
Install Local Conversation History
$ npx skills add daymade/claude-code-skills --skill local-conversation-history -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install daymade/claude-code-skills local-conversation-history --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/daymade-claude-code/local-conversation-history .claude/skills/local-conversation-history && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "local-conversation-history" agent skill from https://github.com/daymade/claude-code-skills/tree/main/daymade-claude-code/local-conversation-history into .claude/skills/local-conversation-history/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-conversation-history", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/daymade/claude-code-skills/tree/main/daymade-claude-code/local-conversation-historyType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add daymade/claude-code-skills --skill local-conversation-history -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install daymade/claude-code-skills local-conversation-history --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/daymade-claude-code/local-conversation-history .agents/skills/local-conversation-history && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "local-conversation-history" agent skill from https://github.com/daymade/claude-code-skills/tree/main/daymade-claude-code/local-conversation-history into .agents/skills/local-conversation-history/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-conversation-history", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add daymade/claude-code-skills --skill local-conversation-history -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install daymade/claude-code-skills local-conversation-history --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/daymade-claude-code/local-conversation-history .cursor/skills/local-conversation-history && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "local-conversation-history" agent skill from https://github.com/daymade/claude-code-skills/tree/main/daymade-claude-code/local-conversation-history into .cursor/skills/local-conversation-history/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-conversation-history", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/daymade/claude-code-skills.git --path daymade-claude-code/local-conversation-history--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add daymade/claude-code-skills --skill local-conversation-history -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install daymade/claude-code-skills local-conversation-history --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/daymade-claude-code/local-conversation-history .gemini/skills/local-conversation-history && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "local-conversation-history" agent skill from https://github.com/daymade/claude-code-skills/tree/main/daymade-claude-code/local-conversation-history into .gemini/skills/local-conversation-history/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-conversation-history", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install daymade/claude-code-skills local-conversation-historyInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add daymade/claude-code-skills --skill local-conversation-history -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/daymade-claude-code/local-conversation-history .github/skills/local-conversation-history && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "local-conversation-history" agent skill from https://github.com/daymade/claude-code-skills/tree/main/daymade-claude-code/local-conversation-history into .github/skills/local-conversation-history/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-conversation-history", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add daymade/claude-code-skills --skill local-conversation-history -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install daymade/claude-code-skills local-conversation-history --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/daymade/claude-code-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/daymade-claude-code/local-conversation-history .opencode/skills/local-conversation-history && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "local-conversation-history" agent skill from https://github.com/daymade/claude-code-skills/tree/main/daymade-claude-code/local-conversation-history into .opencode/skills/local-conversation-history/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-conversation-history", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
local-conversation-history- GitHub stars
- 1.4k
- Token cost
- ~3k tokens
- SKILL.md length
- 1,665 words
- Files
- 1
- Skills in repo
- 104
- Repo updated
- First seen
- Licence
- MIT
At a glance
Entry point for local AI conversation history across Claude Code, Codex and Kimi CLI: routes each request to the reader or continuation skill that owns it and keeps the cross-provider inventory.
- The platform is unknown
- SKILL.md covers Route by platform × action, Provider scope — the job only…, Intent decides the route — the… and Invariants that survive routing, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Plural (what was I working on
What it does
Local Conversation History is an agent skill from daymade/claude-code-skills. Entry point for local AI conversation history across Claude Code, Codex and Kimi CLI: routes each request to the reader or continuation skill that owns it and keeps the cross-provider inventory. Use when the platform is unknown or plural ("what was I working on", "we discussed this once") and for any Kimi CLI history. When platform and action are already clear, load that skill directly.
Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It works with Kimi. The repository describes itself as: Professional Claude Code skills marketplace featuring production-ready skills for enhanced development workflows. The licence is MIT.
When your agent uses it
- The platform is unknown
- Plural (what was I working on
- We discussed this once) and for any Kimi CLI history
Example prompts
- “what was I working on”
- “we discussed this once”
- “/local-conversation-history”
What it can do on your machine
Read from SKILL.md and the folder at commit 0e52df5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Local Conversation History loads about 3k tokens when it runs. Until then it costs about 104 tokens; SKILL.md has 1,665 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from daymade/claude-code-skills at commit 0e52df5, republished under its MIT licence (© daymade). 1,665 words, ~2,998 tokens.
Download SKILL.mdSave it as
.claude/skills/local-conversation-history/SKILL.md (or your agent's skills folder).- name
- local-conversation-history
- description
- Entry point for local AI conversation history across Claude Code, Codex and Kimi CLI: routes each request to the reader or continuation skill that owns it and keeps the cross-provider inventory. Use when the platform is unknown or plural ("what was I working on", "we discussed this once") and for any Kimi CLI history. When platform and action are already clear, load that skill directly.
- argument-hint
- [keywords | session-id | workspace-path]
Local Conversation History — router
This skill decides which skill runs. It does not parse history itself, does not own commands for a single provider, and never re-implements what an executor already does. If you find yourself explaining flags for one provider, you are in the wrong skill — hand off and stop.
Route by platform × action
For a backup-health request ("are our conversation backups working?" / "历史备份是否正常"),
read the owning backup configuration and storage SOP before selecting a history reader.
Use git-large-files-storage-setup's backup-health workflow when that Skill is installed;
otherwise use the existing storage owner's procedure and report any missing dependency.
Keep this route read-only. Verify provider/source coverage, the actual backup round,
destination originals, recovery samples and the alert job separately. Do not resume a
paused collector or rebuild an index to check a backup. Use provider readers only for
selected original/session identity checks, not conversation-body searches to discover
backup jobs. Keep account, machine and credential paths in the user's owning configuration.
Establish two things before routing: which platform the conversation lived on, and whether the user wants evidence (what was said/done) or resumption (take the work forward).
| Platform | Read evidence | Continue the work |
|---|---|---|
| Claude Code | daymade-claude-code:read-claude-code-history | daymade-claude-code:continue-claude-code-work |
| OpenAI Codex | daymade-claude-code:read-codex-history | daymade-claude-code:continue-codex-work |
| Kimi CLI | read-claude-code-history, with the Kimi scope named — see Provider scope | no continuation skill exists |
Resumption always follows a read. The continuation skills require a verified read receipt; routing straight to them without one is a defect, not a shortcut.
When the platform is not stated, separate an exact identity from a memory of content. With a complete session ID, first use the Codex exact-ID locator, then the Claude Code exact-session lookup if Codex does not verify it. The verified original record decides the provider and continuation skill; an ID prefix does not. With only a title, date, quote, or remembered topic, use the inventory or content-search route below and verify the original messages before assigning a provider.
Provider scope — the job only this entry point routes
Name the requested providers before handing off. Inventory and content recall use different executors; do not assume a provider-specific default covers a cross-provider request.
| Cross-provider need | Route to | Name this scope |
|---|---|---|
| Inventory — "what have I been working on", "list my recent chats", session titles/dates/IDs | Indexed metadata where available, then exact-session readers | Do not use list_local_history.py --source all: its date and output limits are applied after Claude session bodies are read. Report a gap if no indexed inventory exists. |
| Content search — "did we ever discuss X", find a quote, file, or tool result | read-claude-code-history, its indexed recall, then exact-session reader | Select the relevant indexed providers; inspect index coverage and freshness. Open only candidate sessions. |
| Ranked recall — wording may have drifted | read-claude-code-history, its hybrid recall index | The index states which providers it holds; do not infer coverage for an unindexed provider. |
Indexed recall accepts explicit Claude, Codex, and Kimi provider filters.
Use supplied clues before broad discovery. For a pasted quote with a known
project, date, or title, use indexed metadata to narrow candidates, then
verify their original messages. For Codex, follow Locate a quoted exchange in
read-codex-history. Inventory alone never establishes a content match; if its
candidates miss or its scope is incomplete, report the gap and refine the indexed query.
Keep the current Session excluded. A request for only an ID stops at verified
message evidence; it does not require reconstructing every unrelated conversation.
Search history through the index or an exact known session. A raw sweep of every conversation is prohibited, including when an output limit or scan timeout is set. The current raw-search date flags filter after files are read, so they do not make that command bounded. If the index is missing, stale, or lacks a provider, report that coverage gap; do not fall back to a corpus scan. Ranked top-K results cannot support an absence claim.
Kimi CLI has no other entry anywhere — no dedicated skill exists for either
axis, so both routes above land in read-claude-code-history, which documents
its own Kimi home resolution.
Let the executor own exact-session lookup, indexed provider filters, coverage, and output format. This skill names which providers are in scope.
Intent decides the route — the word "history" does not
| The user's requested result | Route |
|---|---|
| Whether conversation backups are current and recoverable | The backup-health route above; return separate provider/source and destination verdicts, with coverage and recovery limits |
| A list of conversations: titles, dates, session IDs | The indexed inventory row under Provider scope; if unavailable, state the gap |
| The conversation where a topic, quote, file, or tool result appeared — "find that old chat", "did we ever discuss X" | The indexed content search row under Provider scope; use supplied clues to narrow candidates first. Listing titles alone is not evidence the content exists |
| Their own raw inputs in chronological order, verbatim | The matching reader's verbatim-input path. Preserve duplicates and session boundaries; duplicates are part of the ledger, not noise |
| Recent requests that may have stalled — "anything we recently forgot to finish?" / "最近提过却没推进的事" | The indexed inventory/content-search routes under Provider scope, then the matching exact-session readers. Verify candidates against current project records; a project registry alone does not cover unregistered requests |
| Picking work back up from an identified session | The matching continuation skill, after a read |
The requested output wins over the background motivation. If someone explains a problem and then asks for a window of their own raw inputs, return that window — the explanation's topic clues do not convert the request into a content search.
For a recent-unfinished-work request, keep the retrieval read-only. Establish the requested time window and relevant providers, inspect index freshness, and open only selected sessions through their owning readers. Pair each candidate's original user request with the latest relevant handoff or completion evidence; check the project's current decision/status source before calling it unfinished. Keep completed work, user-paused work, external blockers, and work awaiting acceptance distinct. Treat reminders, assistant plans, and uncompleted reference bookmarks as leads, not proof of an outstanding commitment. Report the candidate, next action, evidence source/date, and any unresolved coverage gap. Stop after the requested inventory; do not resume old work or migrate tasks without that authorization. The calling agent performs this reconciliation; the readers own retrieval, and no mechanical check establishes real-world completion for them.
Show full SKILL.md (631 more words)Show less
Invariants that survive routing
For remembered facts, identify the exact proposition before searching: account count, account users, and an event's execution identity are different questions. Check three evidence lanes in selected sessions: direct user words, assistant retellings as locators, and original external records previously read by tools. An assistant's quote locates the source; it does not replace that source. Use the provider reader's complete tool-evidence route when the target is a prior read.
When the user says “search again”, change a concrete search dimension: source lane, indexed provider/date/project scope, literal versus semantic matching, or the selected session's original records. Do not end the retry with the same ranked prose query and different synonyms alone. State which coverage changed. Keep a found subclaim separate from an unfound remainder; current explicit user facts remain authoritative even when their historical wording is not located. Preserve original evidence values; do not silently redact, replace, or summarize the stored text while exporting a record.
- Coverage. Read the index's provider and source scope plus its freshness frontier. An archive or provider outside that scope is unknown. A missing required source cannot support an absence claim.
- Self-match. The current session records the user's question and this agent's own commands, so it matches almost any query about itself. Exclude the current session ID before treating a hit as historical evidence.
- Zero results are not absence. Ranked recall can miss different wording and unindexed records. State coverage; do not convert an empty result into "it never happened".
- Ask whether a word is the topic's name or the way you talk about it. A
search for
技术选型over a corpus where the user actually said 用哪个 and 不要闭门造车 returns almost nothing — measured: 10 hits against 163 real occurrences, because a Chinese phrase only matches on a token boundary. When searching one person's corpus, search the way they speak: imperatives, negations, and concrete scene sentences, not the label a design document would give the topic. A zero hit on a topic name cannot support an absence claim; widen to the phrasing that person would have used first, and say which forms you tried. - A zero has three causes and only one of them is "no history". The other
two are a home that was never found and a scope that excluded everything, and
none of the three looks different in an empty table. This bites Kimi hardest:
its documented default home is not where every install puts it — a desktop
client can bundle the CLI inside its own runtime and keep sessions there — and
its sessions belong to their own workspaces, so a default run inside some other
repository returns nothing on a store full of conversations. Rule out both
before reporting absence: name the home that was actually read, and say what
project scope was in effect. The inventory prints a diagnostic line when a home
is missing, so quote it when it appears — but a located home that yields
zero prints no diagnostic at all, and the search path prints none in either
case, so never treat a silent empty result as the reader confirming absence.
read-claude-code-historyowns how to locate a home and which scope flags the inventory needs.
Do not
- Do not run provider-specific parsing, SQLite,
rg,jq, or JSONL pipelines here. Every one of those belongs to an executor that already handles its store's schema, archives, and failure modes. - Do not copy an executor's flags into this file beyond the three that name
provider scope (
--source,--codex,--kimi) — those are this skill's own subject. Every other flag changes on the executor's schedule; copying one here makes this file drift silently and then teach the wrong command. - Do not route to a continuation skill to answer a question about the past. Reading is evidence; continuing changes the world.
© daymade, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in daymade-claude-code/local-conversation-history of daymade/claude-code-skills.
Open the folder on GitHubat commit 0e52df5
Compare with similar skills
Local Conversation History next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Local Conversation History this skilldaymade/claude-code-skills | 1.4k | — | ~3k | Automated safety check: Pass | MIT | |
| CCS Task Delegationkaitranntt/ccs | 2.9k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Ccmanager Configkbwo/ccmanager | 1.3k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Kimi WebbridgeMoonshotAI/kimi-code | 7.8k | — | ~3.6k | Automated safety check: Pass | MIT | |
| Open Kimi Pptjinwyp/open-ppt-skill | 161 | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Helmor Bump Vendorsdohooo/helmor | 1.3k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Ccmanager Config
kbwo/ccmanager
Set up, review, or repair a CCManager config — .ccmanager.json at a git repository root, or the global ~/.config/ccmanager/config.json.
Kimi Webbridge
MoonshotAI/kimi-code
Kimi Browser Extension（Kimi 浏览器扩展，原 Kimi WebBridge）lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login…
Open Kimi Ppt
jinwyp/open-ppt-skill
Create, edit, replicate, read, and export presentations. An agent skill from jinwyp/open-ppt-skill.
Helmor Bump Vendors
dohooo/helmor
Bump or upgrade the pinned versions of Helmor's bundled agent CLIs, SDKs, and supporting binaries — Claude Code + claude-agent-sdk (lockstep), Codex, Cursor SDK, OpenCode, Kimi, Pi, and gh / glab /…
Gen Changesets
MoonshotAI/kimi-code
A skill your agent uses when generating changesets in the kimi-code repository — deciding whether to write one, which package to list, the bump level, the wording, and the confirmation workflow.
More from daymade/claude-code-skills
All 104 skills in this repoVideo Comparer
daymade/claude-code-skills
This skill should be used when comparing two videos to analyze compression results or quality differences.
CLI Demo Generator
daymade/claude-code-skills
Generates professional animated CLI demos as GIFs using VHS terminal recordings.
Doc To Markdown
daymade/claude-code-skills
Converts DOCX/PDF/PPTX and saved HTML/HTM to high-quality Markdown with automatic post-processing.
Interaction Design Board
daymade/claude-code-skills
Generates several distinct, clickable HTML interaction prototypes for one product surface into a Design Board and collects selection/remix feedback before implementation.
Skill Creator
daymade/claude-code-skills
Creates, edits and benchmarks skills; supersedes the official skill-creator plugin, so when both are listed, use this one.
Auto Repo Setup
daymade/claude-code-skills
Diagnoses and repairs repository setup and guarded Git workflows for Claude Code or Codex — environment repair, startup sync, hook auditing, collaborator handoff.
Related
Works with
Questions about Local Conversation History
What does Local Conversation History do?
Entry point for local AI conversation history across Claude Code, Codex and Kimi CLI: routes each request to the reader or continuation skill that owns it and keeps the cross-provider inventory. Local Conversation History is an agent skill from daymade/claude-code-skills. Entry point for local AI conversation history across Claude Code, Codex and Kimi CLI: routes each request to the reader or continuation skill that owns it and keeps the cross-provider inventory.
When should I use Local Conversation History?
Local Conversation History fits situations like: the platform is unknown; plural (what was I working on; we discussed this once) and for any Kimi CLI history.
How do I install Local Conversation History in Claude Code?
Run `npx skills add daymade/claude-code-skills --skill local-conversation-history -a claude-code`. Or copy the skill folder (daymade-claude-code/local-conversation-history in daymade/claude-code-skills) into .claude/skills/local-conversation-history in your project. Claude Code loads it when a task matches its description.
How do I install Local Conversation History in Codex?
Run `npx skills add daymade/claude-code-skills --skill local-conversation-history -a codex`. Or copy the skill folder (daymade-claude-code/local-conversation-history in daymade/claude-code-skills) into .agents/skills/local-conversation-history in your project. Codex loads it when a task matches its description.
Can I use Local Conversation History in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add daymade/claude-code-skills --skill local-conversation-history -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/local-conversation-history, .gemini/skills/local-conversation-history, .github/skills/local-conversation-history and .opencode/skills/local-conversation-history in your project.
What does Local Conversation History need to run?
SKILL.md names no scripts, command-line tools or credentials: Local Conversation History is instructions for the agent only.
Does Local Conversation History access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Local Conversation History safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Local Conversation History use?
Local Conversation History is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Local Conversation History use?
About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Local Conversation History?
Skills that share tags, products or a category with Local Conversation History: CCS Task Delegation (kaitranntt/ccs, 2.9k stars), Ccmanager Config (kbwo/ccmanager, 1.3k stars), Kimi Webbridge (MoonshotAI/kimi-code, 7.8k stars) and Open Kimi Ppt (jinwyp/open-ppt-skill, 161 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Local Conversation History?
daymade (a GitHub user) maintains it in daymade/claude-code-skills, which has 1,448 GitHub stars. The repository holds 104 skills in this directory. The repository was last updated on October 10, 2026.
Source: daymade/claude-code-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.