session-management
Context preservation, tiered summarization, resumability
27
19%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/session-management/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is extremely weak across all dimensions. It consists of three abstract noun phrases with no verbs, no concrete actions, no explicit trigger guidance, and no clear domain. It would be nearly impossible for Claude to reliably select this skill from a pool of available skills.
Suggestions
Rewrite using active verbs that describe concrete actions, e.g., 'Summarizes long conversations into tiered summaries, preserves key context across sessions, and enables resuming interrupted workflows.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user wants to resume a previous conversation, needs a summary of discussion history, or asks to preserve context across sessions.'
Clarify the specific domain or use case (e.g., conversation management, session continuity, long-running tasks) to distinguish this skill from general summarization or memory-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses abstract nouns ('context preservation', 'tiered summarization', 'resumability') without describing any concrete actions. There are no verbs indicating what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no 'Use when...' clause and the 'what' is only vaguely implied through abstract noun phrases. | 1 / 3 |
Trigger Term Quality | The terms used are technical jargon ('context preservation', 'resumability', 'tiered summarization') that users would almost never naturally say when requesting help. Users would more likely say things like 'summarize conversation', 'pick up where we left off', or 'remember context'. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's unclear what domain or task it applies to. 'Context preservation' and 'summarization' could overlap with many different skills related to conversations, documents, or data processing. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has a well-designed conceptual framework for session management with clear tiered checkpoints and decision heuristics, but suffers severely from its own anti-pattern of verbosity. The same checkpoint rules are repeated 3-4 times across different sections, and extensive template examples with placeholder content bloat the file enormously. Ironically for a skill about context management and compression, it fails to practice what it preaches — the content should be split across multiple files with SKILL.md serving as a concise overview.
Suggestions
Reduce to ~100 lines by extracting all templates (current-state.md, decisions.md, code-landmarks.md, archive template) into separate bundle files and referencing them from SKILL.md
Eliminate the 3x repetition of checkpoint triggers — define them once in the tiered summarization section and reference that section elsewhere
Remove the anti-patterns section entirely; these are obvious inversions of the stated rules and waste tokens
Cut the CLAUDE.md section and enforcement mechanisms significantly — Claude doesn't need 6 different enforcement mechanisms explained; a single concise 'add to CLAUDE.md' block suffices
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | At ~350+ lines, this skill is extremely verbose. It includes extensive template examples with placeholder content (full decision log entries, full archive templates, full code landmarks tables) that Claude could generate on its own. The same tiered checkpoint system is repeated at least 3 times (main section, CLAUDE.md rules, enforcement mechanisms, quick reference). Anti-patterns section states obvious inversions of the rules already given. | 1 / 3 |
Actionability | The skill provides concrete file templates and directory structures, which is useful. However, much of the guidance is process-oriented rather than executable — it describes when to checkpoint and what to write, but the actual 'actions' are writing markdown files. The bash aliases are concrete but trivial. The templates are helpful but overly detailed examples rather than precise instructions. | 2 / 3 |
Workflow Clarity | The tiered summarization system (Tier 1/2/3) with clear triggers and actions is well-sequenced. The decision heuristic flowchart, session start/end protocols, and checkpoint decision tree provide unambiguous sequencing. The self-audit mechanism at ~20 tool calls serves as a validation checkpoint. | 3 / 3 |
Progressive Disclosure | Everything is in a single monolithic file with no bundle files to reference. The content includes full templates for current-state.md, decisions.md, code-landmarks.md, archive files, CLAUDE.md sections, and compression templates — all inline. This is exactly the kind of content that should be split into separate referenced files (e.g., templates/ directory), especially given the skill is about organizing information across files. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (529 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- alinaqi/claude-bootstrap
- Commit
65efb33
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.